UTC

GPT OSS Safeguard 20B

OpenAI · open weights · served by 12 providers · reasoning

openai/gpt-oss-safeguard-20b

Weights
Open
Released
2025-10-29
Knowledge cutoff
Not stated
Context window
4K
Hugging Face repository

openai/gpt-oss-safeguard-20b at commit 8a11e17b25, last changed 2026-01-14

Licence
apache-2.0
Access
Open download
Library
transformers
Formats
.safetensors

What the Hub's scanners report

3 weight files, 3 with a scan result. No scanner reports an issue with them.

The model at this commit, its 3 weight files with their SHA-256 and its base models.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • AI/ML APIopenai/gpt-oss-safeguard-20b
  • Amazon Bedrockopenai.gpt-oss-safeguard-20b
  • Eden AIamazon/openai.gpt-oss-safeguard-20b
  • Eden AIamazon/openai.gpt-oss-safeguard-20b@us
  • Eden AIgroq/openai/gpt-oss-safeguard-20b
  • Groqopenai/gpt-oss-safeguard-20bbeta
  • Kilo Gatewayopenai/gpt-oss-safeguard-20b
  • LowRouterauto/openai/gpt-oss-safeguard-20b
  • Merge Gatewayopenai/gpt-oss-safeguard-20b
  • NanoGPTopenai/gpt-oss-safeguard-20b
  • OpenRouteropenai/gpt-oss-safeguard-20b
  • Vercel AI Gatewayopenai/gpt-oss-safeguard-20b
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.