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. 12175
    Prev
    Next
    INDEX
    Explanations

    LLM efficiency

    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
     condemned
    -0.09
     condemnation
    -0.09
     condemn
    -0.08
     teen
    -0.07
    Teen
    -0.07
    Bienvenue
    -0.07
    Te
    -0.07
    .respond
    -0.07
     bienvenue
    -0.07
     stage
    -0.07
    POSITIVE LOGITS
     giờ
    0.08
    orfen
    0.08
    ụkụ
    0.08
     glfw
    0.08
     fmap
    0.08
     régimen
    0.08
    րագր
    0.08
    әзар
    0.08
     وتأ
    0.08
     þessa
    0.08
    Activations Density 0.001%

    No Known Activations