© 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. 15-RESID-POST-AA
    11. 16389
    Prev
    Next
    INDEX
    Explanations

    Lagu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'aime
    -0.07
     VERY
    -0.07
    ANEL
    -0.07
     MAIN
    -0.07
    él
    -0.07
    unktion
    -0.07
     Grave
    -0.07
    (Card
    -0.07
     А
    -0.07
     ,,
    -0.07
    POSITIVE LOGITS
     gehiago
    0.08
     vider
    0.08
     swo
    0.08
     videoj
    0.08
     pies
    0.08
     письмен
    0.08
     arbete
    0.08
     電
    0.08
    стоя
    0.07
     posiada
    0.07
    Activations Density 0.000%

    No Known Activations