Model page

openai/gpt-oss-20b pass

downloads 7.6Mlikes 4.9klicense apache-2.0arch gpt_ossparams 21512.0Mupdated 2025-08-26

chat template: not in config · view on Hugging Face ↗

Ingot findings

Static battery clean: safetensors weights, license declared, no template/tokenizer drift detected. Deep battery not yet run. Weights battery: embedding-norm scan over 201088 tokens (BF16, 2880-dim) found 936 undertrained candidates, 0 plain-ASCII. Scanned 2026-08-20 (published from a community scan).

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 936 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the GPU deep battery.

How to fixruntime guardweight-level

Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.

  1. Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
  2. Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
  3. The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

architecturegpt_oss · 24 layers · 2880-dim
parameters21512.0M
vocabulary201,088 tokens
licenseapache-2.0
serializationsafetensors pickle
chat templatenone
glitch-token surface936 undertrained candidates, 0 plain-ASCII
Full fingerprint
architecturesGptOssForCausalLM
librarytransformers
pipelinetext-generation
repo files18 — pickle: metal/model.bin
revision6cee5e81ee83
HF snapshot7.6M downloads · 4.9k likes · updated 2025-08-26 · captured 2026-08-20
embedding tensormodel.embed_tokens.weight · BF16 · 201,088×2880
embedding normsmedian 128.1843 · mean 128.309
lineage checkno claimed base model

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: pass

[![Ingot scan](https://ingot.tools/api/v1/models/openai/gpt-oss-20b/badge.svg)](https://ingot.tools/models/openai/gpt-oss-20b)
Gate it in CI