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. 111799
    Prev
    Next
    INDEX
    Explanations

    French/legal text

    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
     Apartments
    -0.08
     icy
    -0.08
    ović
    -0.08
     igualmente
    -0.08
     بغیر
    -0.08
    västi
    -0.07
     fade
    -0.07
    -0.07
    aré
    -0.07
     أيضًا
    -0.07
    POSITIVE LOGITS
     rallies
    0.10
     economists
    0.08
     науки
    0.08
    参与
    0.08
     economically
    0.08
    证券
    0.08
    财经
    0.08
    Econom
    0.07
    Participation
    0.07
    хы
    0.07
    Activations Density 0.011%

    No Known Activations