© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64718
    Prev
    Next
    INDEX
    Explanations

    请

    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
     گرفتن
    -0.09
     Fernando
    -0.08
    ibilité
    -0.08
    Fernando
    -0.08
     comportement
    -0.08
     technolog
    -0.08
    illante
    -0.08
     lär
    -0.07
     expér
    -0.07
    陽
    -0.07
    POSITIVE LOGITS
     format
    0.10
     formatted
    0.10
    formatted
    0.09
     waarin
    0.09
    格式
    0.09
    YYYY
    0.08
     entidade
    0.08
     wobei
    0.08
     формат
    0.08
    =format
    0.08
    Activations Density 0.002%

    No Known Activations