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. 112097
    Prev
    Next
    INDEX
    Explanations

    dental procedures

    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
     Billion
    -0.08
     peripheral
    -0.08
     vun
    -0.08
    annya
    -0.07
     mbi
    -0.07
    oooo
    -0.07
     Bob
    -0.07
     igjen
    -0.07
     Бога
    -0.07
    anke
    -0.07
    POSITIVE LOGITS
    .delete
    0.09
     exper
    0.08
     couch
    0.08
    	delete
    0.08
     Mines
    0.08
    -minute
    0.08
    帐
    0.07
    ুপ
    0.07
     calculus
    0.07
     demolition
    0.07
    Activations Density 0.003%

    No Known Activations