© 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. 16564
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ês
    -0.09
    ائح
    -0.07
     kol
    -0.07
     ，
    -0.07
     （
    -0.07
     baş
    -0.07
     Bryce
    -0.07
    ,value
    -0.07
     appendix
    -0.07
    ʻa
    -0.07
    POSITIVE LOGITS
     memoria
    0.08
     beam
    0.08
     medicamento
    0.08
     eficiencia
    0.08
    merzen
    0.08
    istant
    0.07
    ensitivity
    0.07
    (...)
    0.07
     stonden
    0.07
    :)↵↵
    0.07
    Activations Density 0.013%

    No Known Activations