© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45572
    Prev
    Next
    INDEX
    Explanations

    Chatbot estimates and answers

    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
    邪
    -0.08
    (title
    -0.08
     Opportunities
    -0.08
    Themes
    -0.08
     mutil
    -0.07
     classical
    -0.07
    ''
    -0.07
     distracting
    -0.07
    Everything
    -0.07
    .undo
    -0.07
    POSITIVE LOGITS
     estimates
    0.16
    是多少
    0.16
     estimating
    0.15
     estim
    0.15
     ranges
    0.15
     estimate
    0.14
     estimated
    0.14
    估
    0.13
     Estimates
    0.13
     estimation
    0.13
    Activations Density 0.104%

    No Known Activations