© 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. 78036
    Prev
    Next
    INDEX
    Explanations

    listen

    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
     volte
    -0.08
    Excluded
    -0.07
     Funk
    -0.07
     Northwestern
    -0.07
     Foster
    -0.07
     PCP
    -0.07
    voi
    -0.07
     cement
    -0.07
    ledning
    -0.07
     Pennsylvania
    -0.07
    POSITIVE LOGITS
     atent
    0.12
    /watch
    0.10
     listening
    0.09
     듣
    0.09
     attent
    0.09
    hin
    0.09
    ค์
    0.09
     внимательно
    0.09
     kepada
    0.08
     louder
    0.08
    Activations Density 0.020%

    No Known Activations