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. 54027
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     plas
    -0.08
    退休
    -0.08
    ậ
    -0.08
     mindfulness
    -0.08
    وبة
    -0.08
     tanti
    -0.08
    教程
    -0.08
    auction
    -0.08
     Retirement
    -0.07
     mulle
    -0.07
    POSITIVE LOGITS
    .mkdir
    0.10
     развед
    0.08
     kamen
    0.08
     확보
    0.08
     जंगल
    0.08
     обслед
    0.08
     ব্র
    0.08
     iler
    0.08
     ventured
    0.07
     riscos
    0.07
    Activations Density 0.017%

    No Known Activations