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. 60987
    Prev
    Next
    INDEX
    Explanations

    Printing to console

    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
    Unnamed
    -0.08
     მხრიდან
    -0.08
     কেন
    -0.08
     ખુ
    -0.08
    Tanggal
    -0.08
     arty
    -0.08
     әп
    -0.08
    פו
    -0.08
    Liter
    -0.08
     մայ
    -0.08
    POSITIVE LOGITS
     Urb
    0.08
    ern
    0.07
     bağlı
    0.07
     request
    0.06
     obd
    0.06
     display
    0.06
     ادامه
    0.06
     infect
    0.06
    ello
    0.06
    	request
    0.06
    Activations Density 0.000%

    No Known Activations