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. 112065
    Prev
    Next
    INDEX
    Explanations

    =>

    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
     üçün
    -0.08
     pono
    -0.08
     olmayan
    -0.08
     minut
    -0.08
     ਕਰਨ
    -0.07
    ելու
    -0.07
     overtime
    -0.07
    abı
    -0.07
     कराने
    -0.07
    /sys
    -0.07
    POSITIVE LOGITS
     resembles
    0.09
    これは
    0.09
     reminiscent
    0.08
     Schl
    0.08
     resemble
    0.08
    สัมพันธ์
    0.08
    ಾಗಿದೆ
    0.07
     Rast
    0.07
    就是说
    0.07
    unud
    0.07
    Activations Density 0.124%

    No Known Activations