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. 43383
    Prev
    Next
    INDEX
    Explanations

    description

    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
     LUA
    -0.09
     oby
    -0.08
     caus
    -0.08
     siy
    -0.08
    upy
    -0.08
     zid
    -0.08
     ty
    -0.08
     Simon
    -0.08
     monte
    -0.08
     Monte
    -0.07
    POSITIVE LOGITS
     toasted
    0.09
     Corolla
    0.08
    .logo
    0.08
     infused
    0.08
     brillant
    0.08
     coats
    0.08
    赛车场
    0.08
    nect
    0.07
     풍
    0.07
     열
    0.07
    Activations Density 0.003%

    No Known Activations