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. 111734
    Prev
    Next
    INDEX
    Explanations

    implies

    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
    沈
    -0.09
     неч
    -0.09
     Шь
    -0.08
    uggle
    -0.08
    ตั้ง
    -0.08
     olímp
    -0.08
     ഉദ്ഘാടനം
    -0.08
    РА
    -0.07
    җан
    -0.07
    хь
    -0.07
    POSITIVE LOGITS
    .im
    0.07
    erc
    0.07
     zout
    0.07
     statements
    0.07
     droit
    0.07
     zz
    0.07
     chores
    0.07
    chemy
    0.07
     ze
    0.07
    $.
    0.07
    Activations Density 0.010%

    No Known Activations