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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11827
    Prev
    Next
    INDEX
    Explanations

    along

    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
     demon
    -0.09
     demons
    -0.09
     draait
    -0.09
    ью
    -0.08
     siker
    -0.08
     nødvend
    -0.08
    核
    -0.08
     thé
    -0.07
    .tpl
    -0.07
     xir
    -0.07
    POSITIVE LOGITS
    沿
    0.10
     entlang
    0.10
    /dist
    0.09
    距离
    0.09
     recorrido
    0.09
    距
    0.09
    _pct
    0.09
    徒歩
    0.09
     दूरी
    0.09
    比例
    0.08
    Activations Density 0.032%

    No Known Activations