diff --git a/examples/model_verification_cards/gpt-oss-120b/card.yaml b/examples/model_verification_cards/gpt-oss-120b/card.yaml
new file mode 100644
index 0000000000..87f39a897b
--- /dev/null
+++ b/examples/model_verification_cards/gpt-oss-120b/card.yaml
@@ -0,0 +1,442 @@
+# Agent-readable model verification card.
+# status: unverified | verified | unsupported | not_applicable
+
+title: gpt_oss_120b
+summary: >
+  Performance scope: pretrain_performance.GB200 uses a tuned canonical
+  performance recipe; timing and throughput metrics from functional training
+  items remain sanity checks rather than optimized performance results.
+  GPT-OSS 120B H100 GPU HF-to-Megatron import, GPU Megatron-to-HF export,
+  manual HF/Megatron forward-pass correlation, deterministic Megatron
+  inference, bounded H100 pretraining, H100 SFT, H100 PEFT, and H100
+  checkpoint resume, H100 SFT export/inference, and H100 long-context SFT are
+  verified. GB200 pretraining performance is verified. CPU conversion remains
+  planned but not yet verified.
+verification_index:
+  model_level:
+    verified:
+      - hf_to_megatron_gpu
+      - megatron_to_hf_gpu
+      - manual_forward_pass
+      - inference
+    unverified:
+      - hf_to_megatron_cpu
+      - megatron_to_hf_cpu
+  training:
+    H100:
+      verified: [pretrain, sft, sft_export_inference, sft_long_context, peft, checkpoint_resume]
+  performance:
+    GB200: verified
+model:
+  hf_id: openai/gpt-oss-120b
+  hf_revision: b5c939de8f754692c1647ca79fbf85e8c1e70f8a  # pragma: allowlist secret
+  architecture: GptOssForCausalLM
+  min_transformers_version: "5.8.0"
+verification_environment:
+  base_container: nvcr.io/nvidia/nemo:26.06
+  bridge_commit: a8038f6d99d8ade33e1b715ba79bc9185b073e59  # pragma: allowlist secret
+
+items:
+  hf_to_megatron_cpu:
+    status: unverified
+    precision: bf16
+    command: >
+      ./scripts/conversion/convert.sh import --executor slurm --device cpu --nodes 1
+      --hf-model openai/gpt-oss-120b
+      --hf-revision b5c939de8f754692c1647ca79fbf85e8c1e70f8a
+      --megatron-path work/model-verification/gpt-oss-120b/cpu-megatron
+      --torch-dtype bfloat16 --trust-remote-code
+    last_verified: null
+    expected_result: >
+      Future verification must import the pinned MXFP4 Hugging Face checkpoint,
+      dequantize it into a reloadable BF16 Megatron checkpoint at iter_0000000,
+      and audit keys, shapes, dtypes, and values against the recorded source
+      revision.
+
+  hf_to_megatron_gpu:
+    status: verified
+    precision: bf16
+    command: >
+      ./scripts/conversion/convert.sh import --executor slurm --device gpu
+      --nodes 4 --gpus-per-node 8
+      --hf-model openai/gpt-oss-120b
+      --hf-revision b5c939de8f754692c1647ca79fbf85e8c1e70f8a
+      --megatron-path work/model-verification/gpt-oss-120b/imported-megatron
+      --torch-dtype bfloat16 --tp 1 --pp 4 --ep 8 --etp 1
+      --trust-remote-code
+    last_verified: 2026-08-10
+    expected_result: >
+      Imports the pinned MXFP4 checkpoint on 32 H100 GPUs and creates a
+      reloadable TP1/PP4/EP8/ETP1 BF16 Megatron checkpoint at iter_0000000
+      with 32 DistCP shards, metadata, train-state, tokenizer, and
+      latest-marker artifacts.
+
+  megatron_to_hf_cpu:
+    status: unverified
+    precision: bf16
+    command: >
+      ./scripts/conversion/convert.sh export --executor slurm --device cpu --nodes 1
+      --hf-model unsloth/gpt-oss-120b-BF16
+      --megatron-path work/model-verification/gpt-oss-120b/cpu-megatron/iter_0000000
+      --hf-path work/model-verification/gpt-oss-120b/cpu-hf-export
+      --torch-dtype bfloat16 --trust-remote-code
+    last_verified: null
+    expected_result: >
+      Future verification must export the CPU-imported checkpoint to a public
+      BF16 Hugging Face layout, strictly reload it as GptOssForCausalLM with
+      attention_bias=true, and audit keys, shapes, dtypes, and values against
+      the BF16 reference semantics.
+
+  megatron_to_hf_gpu:
+    status: verified
+    precision: bf16
+    command: >
+      ./scripts/conversion/convert.sh export --executor slurm --device gpu
+      --nodes 4 --gpus-per-node 8
+      --hf-model unsloth/gpt-oss-120b-BF16
+      --megatron-path work/model-verification/gpt-oss-120b/imported-megatron/iter_0000000
+      --hf-path work/model-verification/gpt-oss-120b/hf-export
+      --torch-dtype bfloat16 --export-weight-dtype bfloat16
+      --distributed-save --tp 1 --pp 4 --ep 8 --etp 1
+      --trust-remote-code
+    last_verified: 2026-08-10
+    expected_result: >
+      Exports the distributed Megatron checkpoint to a reloadable BF16 Hugging
+      Face checkpoint with attention_bias=true. The exported checkpoint has 73
+      safetensors shards and 615 BF16 tensors totaling 116,829,156,672
+      parameters, with no missing, unexpected, shape, dtype, or value
+      mismatches against unsloth/gpt-oss-120b-BF16.
+
+  manual_forward_pass:
+    status: verified
+    precision: bf16
+    command: >
+      ./scripts/inference/infer.sh --nodes 4 --gpus-per-node 8
+      --task model-comparison
+      --hf_model_path openai/gpt-oss-120b
+      --hf-revision b5c939de8f754692c1647ca79fbf85e8c1e70f8a
+      --megatron_model_path work/model-verification/gpt-oss-120b/imported-megatron/iter_0000000
+      --hf-logits-path work/model-verification/gpt-oss-120b/manual-forward/hf_logits_france.pt
+      --tp 1 --pp 4 --ep 8 --etp 1
+      --prompt "The capital of France is the city of"
+      --trust-remote-code
+    last_verified: 2026-08-10
+    expected_result: >
+      Compares pinned OpenAI Hugging Face reference logits and the imported
+      Megatron checkpoint on the prompt "The capital of France is the city of".
+      Both predict next token 12650 (' Paris'); token match is true, cosine
+      similarity is 0.999963, maximum absolute logit difference is 0.250000,
+      and mean absolute logit difference is 0.022671.
+
+  inference:
+    status: verified
+    precision: bf16
+    command: >
+      ./scripts/inference/infer.sh --nodes 4 --gpus-per-node 8
+      --task legacy-full-prefix-generation --legacy-full-prefix
+      --hf_model_path unsloth/gpt-oss-120b-BF16
+      --megatron_model_path work/model-verification/gpt-oss-120b/imported-megatron/iter_0000000
+      --prompt "The capital of France is" --max_new_tokens 32
+      --tp 1 --pp 4 --ep 8 --etp 1
+      --trust-remote-code
+    last_verified: 2026-08-10
+    expected_result: |
+      Completes one synchronous deterministic greedy generation through the
+      non-cached compatibility path. Generated exactly 32 new tokens with this
+      literal completion "
+       Paris.
+
+      Great! If you have any more questions or need further assistance, feel free to ask!
+
+      Sure!
+
+      If there's anything else you'd like to
+      "
+
+  pretrain:
+    H100:
+      status: verified
+      precision: bf16
+      enabled_features: {}
+      command: >
+        ./scripts/training/train.sh --nodes 8 --gpus-per-node 8
+        --recipe gpt_oss_120b_pretrain_config --mode pretrain
+        --dataset megatron-indexed --seq_length 4096 --max_steps 100
+        --lr 3e-4 --min_lr 3e-5 --warmup_iters 40
+        'dataset.blend=[["work/data/rp2/head_01"],null]'
+        dataset.path_to_cache=work/cache/gpt-oss-120b/rp2
+        tokenizer.tokenizer_type=SentencePieceTokenizer
+        tokenizer.tokenizer_model=work/data/rp2/tokenizer.model
+        dataset.random_seed=1234 rng.seed=1234
+        scheduler.lr_decay_iters=100 validation.eval_iters=0 validation.eval_interval=0
+        model.moe_router_force_load_balancing=false
+        ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true
+        rerun_state_machine.check_for_nan_in_loss=true checkpoint.load=null
+        checkpoint.finetune=false checkpoint.save_optim=true checkpoint.save_rng=true
+        --save_dir work/model-verification/gpt-oss-120b/pretrain-reference-checkpoints
+        --save_interval 50 logger.log_interval=1 logger.log_throughput=true
+        logger.tensorboard_dir=null
+      last_verified: 2026-08-11
+      metrics:
+        initial_loss: 10.91136
+        final_loss: 5.828481
+        last_10_steps_step_time_ms_avg: 16664.930
+        last_10_steps_model_tflops_per_gpu_avg: 58.420
+        last_10_steps_tokens_per_second_per_gpu_avg: 1966.285
+      expected_result: >
+        On 64x H100, the command completes exactly 100 bounded pretraining
+        optimizer steps using the recipe-owned GBS/MBS, natural routing, and
+        BF16 configuration. All 100 optimizer-step rows are present exactly
+        once with finite loss, zero skipped iterations, and zero NaN
+        iterations. Loss decreases from 10.91136 to 5.828481, all five metrics
+        are recorded, the post-setup run_config.yaml persists, and complete
+        64-shard iter_0000050 and iter_0000100 checkpoints are saved with
+        metadata, train state, tokenizer artifacts, and latest-checkpoint
+        markers suitable for direct resume.
+
+  sft:
+    H100:
+      status: verified
+      precision: bf16
+      enabled_features:
+        sequence_packing: offline
+      command: >
+        ./scripts/training/train.sh --nodes 4 --gpus-per-node 8
+        --recipe gpt_oss_120b_sft_32gpu_h100_bf16_config --mode sft
+        --dataset tulu3
+        --pretrained_checkpoint work/model-verification/gpt-oss-120b/imported-megatron/iter_0000000
+        --max_steps 100 --seq_length 2048
+        --lr 5e-6 --min_lr 0 --warmup_iters 10
+        'dataset.hf_dataset.split="train[:10000]"'
+        'dataset.hf_dataset.load_kwargs={revision:"b14afda60f1bbebe55d5d2fa1e4df5042f97f8be"}'
+        '++tokenizer.hf_tokenizer_kwargs.revision="b5c939de8f754692c1647ca79fbf85e8c1e70f8a"'
+        dataset.hf_output_root=work/data/tulu3/gpt-oss-120b-sft-2k-b14afda60f1b
+        dataset.hf_rewrite=true dataset.seed=1234 rng.seed=5678
+        dataset.do_validation=false dataset.hf_validation_proportion=null
+        dataset.enable_offline_packing=true
+        +dataset.offline_packing_specs.pad_seq_to_mult=1
+        model.tensor_model_parallel_size=2 model.sequence_parallel=true
+        model.recompute_granularity=selective
+        'model.recompute_modules=[moe_act]'
+        scheduler.lr_decay_iters=100 validation.eval_iters=0 validation.eval_interval=0
+        checkpoint.load=null
+        --save_dir work/model-verification/gpt-oss-120b/sft-2k-checkpoints
+        --save_interval 100 logger.log_interval=1 logger.log_throughput=true
+        logger.tensorboard_dir=null
+      last_verified: 2026-08-12
+      metrics:
+        initial_loss: 6.751403
+        final_loss: 0.7468084
+        last_10_steps_step_time_ms_avg: 8063.150
+        last_10_steps_model_tflops_per_gpu_avg: 33.800
+        last_10_steps_tokens_per_second_per_gpu_avg: 1015.980
+      expected_result: >
+        Completed 100 full-SFT steps from the imported checkpoint on 32x H100
+        with immutable Tulu3 selection, assistant-token masking, offline
+        packing, TP2/SP, and selective MoE-activation recompute. All 100
+        optimizer-step rows are present with finite losses, zero skipped
+        iterations, and zero NaN iterations; loss decreases from 6.751403 to
+        0.7468084. All five metrics are recorded, the checkpoint-local
+        post-setup run_config.yaml persists, and the final full-model
+        checkpoint at iter_0000100 is complete with 32 DistCP shards, metadata,
+        train state, tokenizer artifacts, and latest-checkpoint marker 100.
+
+  sft_export_inference:
+    H100:
+      status: verified
+      precision: bf16
+      depends_on: sft
+      commands:
+        - >
+          ./scripts/conversion/convert.sh export --executor slurm --device gpu
+          --nodes 4 --gpus-per-node 8
+          --hf-model unsloth/gpt-oss-120b-BF16
+          --megatron-path work/model-verification/gpt-oss-120b/sft-2k-checkpoints/iter_0000100
+          --hf-path work/model-verification/gpt-oss-120b/sft-hf-export
+          --torch-dtype bfloat16 --export-weight-dtype bfloat16
+          --distributed-save --tp 2 --pp 4 --ep 8 --etp 1
+          --trust-remote-code
+        - >
+          ./scripts/inference/infer.sh --task hf-inference
+          --nodes 1 --gpus-per-node 1
+          --hf-model work/model-verification/gpt-oss-120b/sft-hf-export
+          --prompt "Name the capital of France and explain its role in one sentence."
+          --max-new-tokens 45 --chat-template --trust-remote-code --device cpu
+      last_verified: 2026-08-13
+      expected_result: |
+        The verified step-100 SFT checkpoint exports to a strict-reloadable BF16
+        Hugging Face checkpoint with architecture GptOssForCausalLM and
+        attention_bias=true. The exported checkpoint has 73 safetensors shards,
+        615 tensors, model.safetensors.index.json total_size 233,658,313,344,
+        tokenizer artifacts, generation_config.json, and chat_template.jinja.
+        The deterministic HF verifier reloads the export on CPU through
+        Transformers with no missing, unexpected, mismatched, or error loading
+        keys and generates exactly 45 new tokens under the 45-token bound. The
+        literal completion is:
+        "finalThe capital of France is Paris, and it serves as the political, economic, and cultural center of the country, housing important institutions such as the French government, major corporations, and world-renowned museums and landmarks."
+
+  sft_long_context:
+    H100:
+      status: verified
+      precision: bf16
+      enabled_features:
+        sequence_packing: offline
+        context_parallel_size: 4
+      command: >
+        ./scripts/training/train.sh --nodes 6 --gpus-per-node 8
+        --recipe gpt_oss_120b_sft_48gpu_h100_bf16_32k_config --mode sft
+        --dataset tulu3
+        --pretrained_checkpoint work/model-verification/gpt-oss-120b/imported-megatron/iter_0000000
+        --max_steps 20 --seq_length 32768
+        --lr 1e-6 --min_lr 0 --warmup_iters 2
+        'dataset.hf_dataset.split="train[:10000]"'
+        'dataset.hf_dataset.load_kwargs={revision:"b14afda60f1bbebe55d5d2fa1e4df5042f97f8be"}'
+        '++tokenizer.hf_tokenizer_kwargs.revision="b5c939de8f754692c1647ca79fbf85e8c1e70f8a"'
+        dataset.hf_output_root=work/data/tulu3/gpt-oss-120b-sft-long-context-32k-cp4-pp6-nofuse-gbs4-b14afda60f1b
+        dataset.hf_rewrite=true dataset.seed=1234 rng.seed=5678
+        dataset.do_validation=false dataset.hf_validation_proportion=null
+        dataset.enable_offline_packing=true
+        +dataset.offline_packing_specs.pad_seq_to_mult=8
+        scheduler.lr_decay_iters=20 validation.eval_iters=0 validation.eval_interval=0
+        checkpoint.load=null checkpoint.save=null
+        logger.log_interval=1 logger.log_throughput=true
+        logger.tensorboard_dir=null
+      last_verified: 2026-08-13
+      metrics:
+        initial_loss: 6.666666
+        final_loss: 1.238030
+        last_10_steps_step_time_ms_avg: 24388.780
+        last_10_steps_model_tflops_per_gpu_avg: 5.070
+        last_10_steps_tokens_per_second_per_gpu_avg: 111.964
+      expected_result: >
+        Completed 20 long-context full-SFT optimizer steps from the imported
+        checkpoint on 48x H100 with 32K sequence length, immutable Tulu3
+        selection, assistant-token masking, offline packing, TP2/SP, CP4 with
+        a2a context-parallel communication, PP6, EP4, disabled cross-entropy
+        and bias-activation fusions, and selective MoE-activation recompute.
+        All 20 optimizer-step rows are present exactly once with finite losses,
+        zero skipped iterations, and zero NaN iterations. Loss decreases from
+        6.666666 to 1.238030, all five metrics are recorded, and no checkpoint
+        is saved because this bounded long-context verification run disables
+        checkpoint output.
+
+  peft:
+    H100:
+      status: verified
+      precision: bf16
+      enabled_features:
+        sequence_packing: offline
+      command: >
+        ./scripts/training/train.sh --nodes 1 --gpus-per-node 8
+        --recipe gpt_oss_120b_peft_8gpu_h100_bf16_config --mode lora
+        --dataset tulu3
+        --pretrained_checkpoint work/model-verification/gpt-oss-120b/imported-megatron/iter_0000000
+        --max_steps 100 --seq_length 2048
+        --lr 1e-4 --min_lr 0 --warmup_iters 10
+        'dataset.hf_dataset.split="train[:10000]"'
+        'dataset.hf_dataset.load_kwargs={revision:"b14afda60f1bbebe55d5d2fa1e4df5042f97f8be"}'
+        '++tokenizer.hf_tokenizer_kwargs.revision="b5c939de8f754692c1647ca79fbf85e8c1e70f8a"'
+        dataset.hf_output_root=work/data/tulu3/gpt-oss-120b-peft-2k-b14afda60f1b
+        dataset.hf_rewrite=true dataset.seed=1234 rng.seed=5678
+        dataset.do_validation=false dataset.hf_validation_proportion=null
+        dataset.enable_offline_packing=true
+        +dataset.offline_packing_specs.pad_seq_to_mult=1
+        scheduler.lr_decay_iters=100 validation.eval_iters=0 validation.eval_interval=0
+        checkpoint.load=null
+        --save_dir work/model-verification/gpt-oss-120b/peft-2k-checkpoints
+        --save_interval 100 logger.log_interval=1 logger.log_throughput=true
+        logger.tensorboard_dir=null
+      last_verified: 2026-08-11
+      metrics:
+        initial_loss: 6.667154
+        final_loss: 0.9883968
+        last_10_steps_step_time_ms_avg: 11509.100
+        last_10_steps_model_tflops_per_gpu_avg: 89.850
+        last_10_steps_tokens_per_second_per_gpu_avg: 2847.138
+      expected_result: >
+        Completed 100 LoRA steps from the imported checkpoint with the base
+        frozen, model-native target modules, immutable Tulu3 selection,
+        assistant-token masking, and offline packing. All 100 optimizer-step
+        rows are present with finite losses, zero skipped iterations, and zero
+        NaN iterations; the checkpoint-local post-setup run_config.yaml
+        persists and latest_checkpointed_iteration.txt points to the reloadable
+        final adapter checkpoint at iter_0000100.
+
+  checkpoint_resume:
+    H100:
+      status: verified
+      precision: bf16
+      depends_on: pretrain
+      command: >
+        ./scripts/training/train.sh --nodes 8 --gpus-per-node 8
+        --recipe gpt_oss_120b_pretrain_config --mode pretrain
+        --dataset megatron-indexed --seq_length 4096 --max_steps 100
+        --lr 3e-4 --min_lr 3e-5 --warmup_iters 40
+        'dataset.blend=[["work/data/rp2/head_01"],null]'
+        dataset.path_to_cache=work/cache/gpt-oss-120b/rp2
+        tokenizer.tokenizer_type=SentencePieceTokenizer
+        tokenizer.tokenizer_model=work/data/rp2/tokenizer.model
+        dataset.random_seed=1234 rng.seed=1234
+        scheduler.lr_decay_iters=100 validation.eval_iters=0 validation.eval_interval=0
+        model.moe_router_force_load_balancing=false
+        ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true
+        rerun_state_machine.check_for_nan_in_loss=true
+        checkpoint.ckpt_step=50 checkpoint.finetune=false
+        --load_dir work/model-verification/gpt-oss-120b/pretrain-reference-checkpoints
+        --save_dir work/model-verification/gpt-oss-120b/pretrain-resume-checkpoints
+        --save_interval 50 logger.log_interval=1 logger.log_throughput=true
+        logger.tensorboard_dir=null
+      last_verified: 2026-08-11
+      metrics:
+        initial_loss: 6.489011
+        final_loss: 5.825046
+        last_10_steps_step_time_ms_avg: 16625.300
+        last_10_steps_model_tflops_per_gpu_avg: 58.560
+        last_10_steps_tokens_per_second_per_gpu_avg: 1970.972
+      resume_comparison:
+        reference_item: pretrain
+        sentinel_steps: [51, 100]
+        loss_relative_tolerance: 1.0e-2
+        loss_absolute_tolerance: 1.0e-6
+        sentinels_match: true
+      expected_result: >
+        The command restores optimizer, scheduler, data-order, and RNG state
+        directly from the verified pretrain step-50 checkpoint into a distinct
+        output root and executes exactly steps 51 through 100. All 50 resumed
+        optimizer-step rows are present exactly once with finite loss, zero
+        skipped iterations, and zero NaN iterations. The step-51 loss matches
+        the reference exactly at 6.489011, and the step-100 loss 5.825046 is
+        within the declared one percent relative plus 1e-6 absolute gate
+        against reference loss 5.828481. All five metrics are recorded, the
+        post-setup run_config.yaml persists, and the final step-100 checkpoint
+        is complete with 64 DistCP shards, metadata, train state, tokenizer
+        artifacts, and latest-checkpoint marker 100.
+
+  pretrain_performance:
+    GB200:
+      status: verified
+      precision: bf16
+      command: >
+        ./scripts/training/train.sh --nodes 16 --gpus-per-node 4
+        --recipe gpt_oss_120b_pretrain_64gpu_gb200_bf16_config
+        --mode pretrain --max_steps 50 logger.log_throughput=true
+      last_verified: 2026-08-17
+      metrics:
+        initial_loss: 12.79104
+        final_loss: 0.03246120
+        last_10_steps_step_time_ms_avg: 4995.630
+        last_10_steps_model_tflops_per_gpu_avg: 535.230
+        last_10_steps_tokens_per_second_per_gpu_avg: 16398.332
+      expected_result: >
+        On exactly 64 GB200s, the canonical BF16 mock-data performance recipe
+        completes 50 optimizer steps at TP1/PP1/CP1/EP64/ETP1, GBS/MBS
+        1280/4, forced router balancing, selective layernorm and MoE
+        activation recompute, and expert-parallel communication overlap. All
+        50 optimizer-step rows are present exactly once with finite loss, zero
+        skipped iterations, and zero NaN iterations. Loss decreases from
+        12.79104 to 0.03246120. The final ten logged step times average
+        4995.630 ms, measured model throughput averages 535.230 TFLOP/s/GPU,
+        and derived token-slot throughput averages 16398.332 tokens/s/GPU over
+        the same final-ten window. The resolved configuration persists. Mock
+        data and forced routing make the loss a finiteness check rather than
+        convergence evidence.
diff --git a/src/megatron/bridge/recipes/gpt_oss/__init__.py b/src/megatron/bridge/recipes/gpt_oss/__init__.py
index dbece3cc5b..dd2902aaef 100644
--- a/src/megatron/bridge/recipes/gpt_oss/__init__.py
+++ b/src/megatron/bridge/recipes/gpt_oss/__init__.py
@@ -26,6 +26,7 @@
     gpt_oss_20b_sft_openmathinstruct2_thinking_packed_config,
     gpt_oss_120b_peft_config,
     gpt_oss_120b_pretrain_config,
+    gpt_oss_120b_sft_32k_config,
     gpt_oss_120b_sft_config,
 )
 
@@ -34,6 +35,7 @@
     "gpt_oss_20b_pretrain_config",
     "gpt_oss_20b_pretrain_fp8_current_scaling_config",
     "gpt_oss_120b_pretrain_config",
+    "gpt_oss_120b_sft_32k_config",
     "gpt_oss_20b_sft_config",
     "gpt_oss_20b_sft_32k_config",
     "gpt_oss_20b_sft_openmathinstruct2_thinking_packed_config",
diff --git a/src/megatron/bridge/recipes/gpt_oss/gpt_oss.py b/src/megatron/bridge/recipes/gpt_oss/gpt_oss.py
index b358353583..9c88163d1c 100644
--- a/src/megatron/bridge/recipes/gpt_oss/gpt_oss.py
+++ b/src/megatron/bridge/recipes/gpt_oss/gpt_oss.py
@@ -62,11 +62,15 @@
 from megatron.bridge.recipes.gpt_oss.h100.gpt_oss import (
     gpt_oss_120b_sft_32gpu_h100_bf16_config as gpt_oss_120b_sft_config,
 )
+from megatron.bridge.recipes.gpt_oss.h100.gpt_oss import (
+    gpt_oss_120b_sft_48gpu_h100_bf16_32k_config as gpt_oss_120b_sft_32k_config,
+)
 
 
 __all__ = [
     "gpt_oss_120b_peft_config",
     "gpt_oss_120b_pretrain_config",
+    "gpt_oss_120b_sft_32k_config",
     "gpt_oss_120b_sft_config",
     "gpt_oss_20b_peft_config",
     "gpt_oss_20b_peft_fp8_current_scaling_config",
diff --git a/src/megatron/bridge/recipes/gpt_oss/h100/__init__.py b/src/megatron/bridge/recipes/gpt_oss/h100/__init__.py
index 65d341fef7..08121f4ac9 100644
--- a/src/megatron/bridge/recipes/gpt_oss/h100/__init__.py
+++ b/src/megatron/bridge/recipes/gpt_oss/h100/__init__.py
@@ -19,6 +19,7 @@
     "gpt_oss_120b_peft_8gpu_h100_bf16_config",
     "gpt_oss_120b_pretrain_64gpu_h100_bf16_config",
     "gpt_oss_120b_sft_32gpu_h100_bf16_config",
+    "gpt_oss_120b_sft_48gpu_h100_bf16_32k_config",
     "gpt_oss_20b_peft_1gpu_h100_bf16_config",
     "gpt_oss_20b_peft_1gpu_h100_fp8cs_config",
     "gpt_oss_20b_peft_1gpu_h100_fp8mx_config",
diff --git a/src/megatron/bridge/recipes/gpt_oss/h100/gpt_oss.py b/src/megatron/bridge/recipes/gpt_oss/h100/gpt_oss.py
index 195bb24adf..15b13096c1 100644
--- a/src/megatron/bridge/recipes/gpt_oss/h100/gpt_oss.py
+++ b/src/megatron/bridge/recipes/gpt_oss/h100/gpt_oss.py
@@ -568,6 +568,46 @@ def gpt_oss_120b_sft_32gpu_h100_bf16_config() -> ConfigContainer:
     return cfg
 
 
+def gpt_oss_120b_sft_48gpu_h100_bf16_32k_config() -> ConfigContainer:
+    """Return the 32K-context full SFT config for GPT-OSS 120B.
+
+    Default parallelism: TP=2, PP=6, CP=4, EP=4
+
+    Returns:
+        ConfigContainer with settings pre-configured for GPT-OSS 120B long-context SFT.
+    """
+    cfg = gpt_oss_120b_sft_32gpu_h100_bf16_config()
+
+    seq_length = 32768
+    cfg.model.seq_length = seq_length
+    cfg.dataset.seq_length = seq_length
+    cfg.dataset.offline_packing_specs.packed_sequence_size = seq_length
+    cfg.dataset.offline_packing_specs.pad_seq_to_mult = 8
+
+    cfg.model.tensor_model_parallel_size = 2
+    cfg.model.sequence_parallel = True
+    cfg.model.context_parallel_size = 4
+    cfg.model.pipeline_model_parallel_size = 6
+    cfg.model.expert_model_parallel_size = 4
+    cfg.model.cp_comm_type = "a2a"
+    cfg.model.calculate_per_token_loss = True
+
+    cfg.model.cross_entropy_loss_fusion = False
+    cfg.model.bias_activation_fusion = False
+    cfg.model.recompute_granularity = "selective"
+    cfg.model.recompute_modules = ["moe_act"]
+
+    cfg.train.global_batch_size = 4
+    cfg.train.micro_batch_size = 1
+    cfg.ddp.average_in_collective = False
+
+    # Keep the complete process environment visible on the recipe.
+    cfg.env_vars = {
+        **COMMON_RECIPE_ENV_VARS,
+    }
+    return cfg
+
+
 def gpt_oss_20b_sft_8gpu_h100_fp8cs_config() -> ConfigContainer:
     """Return a full SFT config for GPT-OSS 20B with Hopper FP8 current scaling."""
     cfg = gpt_oss_20b_sft_8gpu_h100_bf16_config()
@@ -946,6 +986,7 @@ def gpt_oss_20b_sft_8gpu_h100_bf16_openmathinstruct2_thinking_packed_config() ->
     "gpt_oss_120b_peft_8gpu_h100_bf16_config",
     "gpt_oss_120b_pretrain_64gpu_h100_bf16_config",
     "gpt_oss_120b_sft_32gpu_h100_bf16_config",
+    "gpt_oss_120b_sft_48gpu_h100_bf16_32k_config",
     "gpt_oss_20b_peft_1gpu_h100_bf16_config",
     "gpt_oss_20b_peft_1gpu_h100_fp8cs_config",
     "gpt_oss_20b_peft_1gpu_h100_fp8mx_config",
diff --git a/tests/unit_tests/skills/create_model_verification_card/test_validate_card.py b/tests/unit_tests/skills/create_model_verification_card/test_validate_card.py
index 949ece497d..89f5e199e2 100644
--- a/tests/unit_tests/skills/create_model_verification_card/test_validate_card.py
+++ b/tests/unit_tests/skills/create_model_verification_card/test_validate_card.py
@@ -33,6 +33,12 @@
     ("glm5-2", "peft", "GB200"): (2048, 32, 192),
     ("glm5-2", "checkpoint_resume", "H100"): (2048, 1024, 352),
     ("glm5-2", "checkpoint_resume", "GB200"): (4096, 1024, 192),
+    ("gpt-oss-120b", "pretrain", "H100"): (4096, 512, 64),
+    ("gpt-oss-120b", "sft", "H100"): (2048, 128, 32),
+    ("gpt-oss-120b", "sft_long_context", "H100"): (32768, 4, 48),
+    ("gpt-oss-120b", "peft", "H100"): (2048, 128, 8),
+    ("gpt-oss-120b", "checkpoint_resume", "H100"): (4096, 512, 64),
+    ("gpt-oss-120b", "pretrain_performance", "GB200"): (4096, 1280, 64),
     ("gpt-oss-20b", "pretrain", "H100"): (4096, 512, 16),
     ("gpt-oss-20b", "sft", "H100"): (2048, 128, 8),
     ("gpt-oss-20b", "sft_long_context", "H100"): (32768, 32, 8),