Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90230
    Prev
    Next
    INDEX
    Explanations

    anomaly

    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
     peacefully
    -0.08
     ashes
    -0.07
     www
    -0.07
     wez
    -0.07
     women's
    -0.07
     woman's
    -0.07
     tribute
    -0.07
    ادات
    -0.07
     yards
    -0.07
     girl
    -0.07
    POSITIVE LOGITS
    (score
    0.09
     detectors
    0.08
    Detection
    0.08
    -score
    0.08
     rejecting
    0.08
    Reject
    0.08
     বিচ
    0.08
    嫌
    0.08
     Reject
    0.08
     Detection
    0.08
    Activations Density 0.003%

    No Known Activations