© 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. 95278
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
     leader
    -0.08
     comparable
    -0.08
     statistic
    -0.08
    手续费
    -0.08
     respeto
    -0.08
    协调
    -0.08
     Leader
    -0.08
    স্প
    -0.08
     Conservative
    -0.08
     summary
    -0.07
    POSITIVE LOGITS
    erglass
    0.08
    _utils
    0.08
     nect
    0.08
    _limits
    0.08
    plits
    0.08
     Insolvenz
    0.08
    ิส
    0.08
    foreach
    0.08
    _are
    0.07
    UIScreen
    0.07
    Activations Density 0.036%

    No Known Activations