Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58350
    Prev
    Next
    INDEX
    Explanations

    chat

    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
     ৰাজ
    -0.09
     රා
    -0.09
    Recruit
    -0.09
     COPYING
    -0.08
     ë
    -0.08
     descubre
    -0.08
     scare
    -0.08
     ბევრი
    -0.08
    Ham
    -0.08
     recrut
    -0.08
    POSITIVE LOGITS
    assistant
    0.09
     assistants
    0.09
     assistant
    0.09
     format
    0.09
    助手
    0.09
    	format
    0.08
     Format
    0.08
     Assistant
    0.08
    _format
    0.08
    中的
    0.08
    Activations Density 0.008%

    No Known Activations