© 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. 47876
    Prev
    Next
    INDEX
    Explanations

    SOC

    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
    956
    -0.08
     swimmers
    -0.08
     Obama
    -0.08
     হচ
    -0.08
     NSInteger
    -0.07
     gratitude
    -0.07
    NSInteger
    -0.07
    ılmış
    -0.07
     gemäß
    -0.07
    persons
    -0.07
    POSITIVE LOGITS
     aure
    0.08
    报告
    0.08
    Expose
    0.08
    (AST
    0.07
    (auth
    0.07
     noe
    0.07
     PPT
    0.07
    (Z
    0.07
    指出
    0.07
    0.07
    Activations Density 0.001%
    No Known Activations