Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 74782
    Prev
    Next
    INDEX
    Explanations

    investigation

    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
    าต
    -0.08
    ెక్టర్
    -0.08
     pedi
    -0.07
     deix
    -0.07
     pcl
    -0.07
    पाल
    -0.07
    Pand
    -0.07
    ító
    -0.07
     usados
    -0.07
    φερ
    -0.07
    POSITIVE LOGITS
    ph
    0.10
     festgestellt
    0.09
     feststellen
    0.09
     Showtime
    0.08
     :)↵
    0.08
    ,我
    0.08
     провед
    0.08
     gen
    0.08
    orous
    0.08
    /ph
    0.08
    Activations Density 0.015%

    No Known Activations