© 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. 7-RESID-POST-AA
    11. 1252
    Prev
    Next
    INDEX
    Explanations

    gradient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fidd
    -0.07
     frontier
    -0.07
     Garrett
    -0.07
     attractiveness
    -0.07
     namin
    -0.07
     sap
    -0.07
     அவ
    -0.07
     variance
    -0.07
     differential
    -0.07
     स्म
    -0.07
    POSITIVE LOGITS
    Ascending
    0.09
     czym
    0.08
    자로
    0.08
    бы
    0.08
    FB
    0.08
     англий
    0.08
     Kino
    0.08
    Descending
    0.08
     bose
    0.07
     keď
    0.07
    Activations Density 0.000%

    No Known Activations