© 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. 99473
    Prev
    Next
    INDEX
    Explanations

    jaws and teeth

    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
     explores
    -0.08
     sufrido
    -0.08
    Guid
    -0.07
     galvan
    -0.07
     suffers
    -0.07
     sofreu
    -0.07
    Site
    -0.07
    -site
    -0.07
    ihan
    -0.07
    เช
    -0.07
    POSITIVE LOGITS
     gape
    0.12
     mandíbula
    0.12
     jaw
    0.12
    jaw
    0.11
     jaws
    0.11
    嘴
    0.10
     العسكرية
    0.10
     الأسنان
    0.10
     dentures
    0.10
     dientes
    0.09
    Activations Density 0.008%

    No Known Activations