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. 106151
    Prev
    Next
    INDEX
    Explanations

    BR or L

    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
     வேண்டும்
    -0.08
     lokale
    -0.08
     தெர
    -0.07
    -0.07
    ossier
    -0.07
     ジ
    -0.07
     Ablauf
    -0.07
     Fetch
    -0.07
    local
    -0.07
     stalls
    -0.07
    POSITIVE LOGITS
     nghiên
    0.08
    ọd
    0.08
    /gpl
    0.08
    DISC
    0.08
    ),(
    0.08
     נא
    0.08
     приб
    0.08
    ILON
    0.08
    预测软件
    0.08
    igh
    0.08
    Activations Density 0.001%

    No Known Activations