© 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. 49
    Prev
    Next
    INDEX
    Explanations

    Cinema history

    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
    主义
    -0.08
     Rights
    -0.08
    浴
    -0.08
     Bình
    -0.08
     Isaiah
    -0.08
     literally
    -0.07
     booty
    -0.07
     Indicators
    -0.07
    ,List
    -0.07
     Đức
    -0.07
    POSITIVE LOGITS
    urat
    0.08
     предвар
    0.08
    ето
    0.08
     траг
    0.08
     Trem
    0.07
     koll
    0.07
    нят
    0.07
    alg
    0.07
    wat
    0.07
    ерв
    0.07
    Activations Density 0.000%

    No Known Activations