© 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. 94708
    Prev
    Next
    INDEX
    Explanations

    Forms and foreign language

    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
     CDN
    -0.09
     crunch
    -0.09
     Tween
    -0.09
     chalk
    -0.09
     anaer
    -0.09
     emoji
    -0.09
     Meetup
    -0.09
     nerve
    -0.09
    Emoji
    -0.09
     wasm
    -0.09
    POSITIVE LOGITS
    .Rows
    0.11
     JTable
    0.10
    .Row
    0.10
    cursor
    0.10
    Rows
    0.10
     Rows
    0.10
    CRUD
    0.10
    -row
    0.10
    Row
    0.09
    Displayed
    0.09
    Activations Density 0.008%

    No Known Activations