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. 58779
    Prev
    Next
    INDEX
    Explanations

    religion

    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
    toe
    -0.08
    (*
    -0.08
    thor
    -0.08
     sleeve
    -0.08
    ocin
    -0.08
     મોક
    -0.08
    cone
    -0.07
    hole
    -0.07
     meth
    -0.07
    -before
    -0.07
    POSITIVE LOGITS
    /legal
    0.09
    用品
    0.08
     deed
    0.08
     persecution
    0.08
     ism
    0.08
     terrorism
    0.08
     ವಿಷಯ
    0.08
    Countdown
    0.07
     व्यवस्था
    0.07
    .about
    0.07
    Activations Density 0.008%

    No Known Activations