© 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. 3-RESID-POST-AA
    11. 12990
    Prev
    Next
    INDEX
    Explanations

    判断

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Consult
    -0.09
     spokes
    -0.08
     mö
    -0.08
    bie
    -0.08
     canned
    -0.08
     avenues
    -0.08
     consult
    -0.08
     Viva
    -0.08
    ixe
    -0.08
     rota
    -0.08
    POSITIVE LOGITS
     조건
    0.09
    判断
    0.09
     условий
    0.09
     условия
    0.09
    조건
    0.09
     判断
    0.09
    条件
    0.08
     explosion
    0.08
     explode
    0.08
     Condition
    0.08
    Activations Density 0.023%

    No Known Activations