Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111433
    Prev
    Next
    INDEX
    Explanations

    Vanessa

    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
     মৃত্যু
    -0.08
     koszt
    -0.08
     otherwise
    -0.08
     मृत्यु
    -0.08
     وقف
    -0.08
     Arabia
    -0.08
    Sag
    -0.08
     ставка
    -0.08
     sag
    -0.08
     Sag
    -0.07
    POSITIVE LOGITS
    Fade
    0.08
    _FA
    0.07
    iju
    0.07
    Anne
    0.07
    ెన్
    0.07
    రి
    0.07
    [df
    0.07
    '$
    0.07
     soaking
    0.07
    "It
    0.07
    Activations Density 0.000%

    No Known Activations