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. 12790
    Prev
    Next
    INDEX
    Explanations

    Racket sports

    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
     myocard
    -0.08
    .Book
    -0.07
     Krypt
    -0.07
    andes
    -0.07
     pagan
    -0.07
     повыш
    -0.07
    icat
    -0.07
     Books
    -0.07
     Infl
    -0.07
    (Book
    -0.07
    POSITIVE LOGITS
     tenis
    0.10
     opponent
    0.08
    طي
    0.08
     badminton
    0.08
     ισ
    0.08
     ump
    0.08
     etiquette
    0.08
    Courtesy
    0.08
     comunicación
    0.08
     antenna
    0.08
    Activations Density 0.009%

    No Known Activations