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. 43961
    Prev
    Next
    INDEX
    Explanations

    electronic

    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
    หน้
    -0.08
    ları
    -0.08
    Raz
    -0.08
     Como
    -0.07
    locale
    -0.07
    lap
    -0.07
    webkit
    -0.07
     raz
    -0.07
     прор
    -0.07
     Jog
    -0.07
    POSITIVE LOGITS
     leaning
    0.08
     warfare
    0.08
     Warfare
    0.08
    召
    0.08
     Ati
    0.08
     Sant
    0.07
    /ph
    0.07
     Commerce
    0.07
     memper
    0.07
     fastening
    0.07
    Activations Density 0.005%

    No Known Activations