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. 56238
    Prev
    Next
    INDEX
    Explanations

    Extension

    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
     autoplay
    -0.08
    Placeholder
    -0.08
    SOC
    -0.08
     baw
    -0.08
    Privacy
    -0.07
     privacy
    -0.07
    еться
    -0.07
     reds
    -0.07
    ち
    -0.07
    -flow
    -0.07
    POSITIVE LOGITS
    vergoeding
    0.08
     Sedan
    0.08
     tuner
    0.08
     Rubber
    0.07
     Farn
    0.07
     Puebla
    0.07
     Aircraft
    0.07
     Vf
    0.07
     sichern
    0.07
    _util
    0.07
    Activations Density 0.000%

    No Known Activations