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

    Neuronpedia

    APICircuit 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. 106241
    Prev
    Next
    INDEX
    Explanations

    Mixed language/personal narratives

    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
     staging
    -0.10
     pico
    -0.08
    摆
    -0.08
    .sol
    -0.08
     staged
    -0.08
     Sol
    -0.07
     솔
    -0.07
     bursting
    -0.07
    Sol
    -0.07
    Ch
    -0.07
    POSITIVE LOGITS
    visitor
    0.09
    (clazz
    0.09
    (visitor
    0.09
     Besucher
    0.08
     bedienen
    0.08
     Visitor
    0.08
     посет
    0.08
    waju
    0.08
     voudrais
    0.08
     Borough
    0.07
    Activations Density 0.001%

    No Known Activations