© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99247
    Prev
    Next
    INDEX
    Explanations

    Safety/Vulnerability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    物流
    -0.08
     phủ
    -0.08
     seamless
    -0.07
     skil
    -0.07
    发生
    -0.07
     gif
    -0.07
     seamlessly
    -0.07
    �
    -0.07
     skiing
    -0.07
    融合
    -0.07
    POSITIVE LOGITS
     advisable
    0.10
    security
    0.09
     recomend
    0.09
     recommandé
    0.09
     recomendado
    0.09
     Consider
    0.09
    _SECURITY
    0.09
     precautions
    0.09
     recomendable
    0.09
     recomendamos
    0.09
    Activations Density 0.014%

    No Known Activations