© 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. 129496
    Prev
    Next
    INDEX
    Explanations

    format

    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
    实力
    -0.08
     çeşitli
    -0.08
     다양한
    -0.08
    )is
    -0.08
    -appointed
    -0.07
     db
    -0.07
     _)
    -0.07
    (db
    -0.07
    �
    -0.07
     berbagai
    -0.07
    POSITIVE LOGITS
     pár
    0.09
     sandwich
    0.09
     format
    0.09
     obey
    0.09
     pattern
    0.08
     الآ
    0.08
    YYYY
    0.08
     формат
    0.07
    形式
    0.07
     salido
    0.07
    Activations Density 0.008%

    No Known Activations