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. 11959
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    .Surface
    -0.08
    .Table
    -0.08
     ";
    -0.08
     Aside
    -0.07
    -cl
    -0.07
     основания
    -0.07
     Dual
    -0.07
     específica
    -0.07
     הק
    -0.07
    <Location
    -0.07
    POSITIVE LOGITS
     llevaron
    0.08
    arry
    0.08
     realizaron
    0.08
     llevando
    0.07
     réalisés
    0.07
     giants
    0.07
     lieber
    0.07
    র্ধ
    0.07
    uiste
    0.07
    ਾਰੇ
    0.07
    Activations Density 0.104%

    No Known Activations