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. 44047
    Prev
    Next
    INDEX
    Explanations

    3

    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
     sa
    -0.08
     chez
    -0.07
     shel
    -0.07
     south
    -0.07
     desk
    -0.07
    zar
    -0.07
     sous
    -0.07
    [y
    -0.07
     Hai
    -0.07
     उज
    -0.07
    POSITIVE LOGITS
    以上
    0.09
     Duitse
    0.08
     teken
    0.08
    ોધ
    0.08
     Eu
    0.07
     (€
    0.07
     الأوروبي
    0.07
    wow
    0.07
    selected
    0.07
    (download
    0.07
    Activations Density 0.002%

    No Known Activations