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. 94963
    Prev
    Next
    INDEX
    Explanations

    auto repair shops

    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
    peater
    -0.09
     maps
    -0.08
     شاعر
    -0.08
    .spacing
    -0.08
     poet
    -0.08
     już
    -0.08
     Meditation
    -0.08
    epsilon
    -0.08
    _embedding
    -0.08
     sijo
    -0.08
    POSITIVE LOGITS
    维修
    0.15
     machining
    0.12
     ремонт
    0.11
     تعمیر
    0.11
     technicians
    0.10
     technician
    0.10
     repairing
    0.10
     Repar
    0.10
     repairs
    0.10
     ремон
    0.10
    Activations Density 0.064%

    No Known Activations