© 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. 2696
    Prev
    Next
    INDEX
    Explanations

    /

    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
     অব
    -0.08
    器
    -0.08
     Mis
    -0.07
    Mis
    -0.07
     impair
    -0.07
    经
    -0.07
    -0.07
     ciment
    -0.07
    Inc
    -0.07
    即可
    -0.07
    POSITIVE LOGITS
    GBP
    0.08
     prév
    0.08
     Unterhaltung
    0.08
     Stanton
    0.08
     EMP
    0.08
    مه
    0.07
     ه
    0.07
     ally
    0.07
     बे
    0.07
     Birch
    0.07
    Activations Density 0.038%
    No Known Activations