© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1320
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.08
     sécur
    -0.07
    Dias
    -0.07
    Dell
    -0.07
    bb
    -0.07
     demol
    -0.07
     кур
    -0.07
     sauveg
    -0.07
     средств
    -0.07
     Prague
    -0.07
    POSITIVE LOGITS
     Überg
    0.08
     controlador
    0.08
    icije
    0.08
    icii
    0.08
     dominio
    0.08
     Vorg
    0.07
     gráfico
    0.07
     Grosso
    0.07
    ertet
    0.07
    /controller
    0.07
    Activations Density 0.000%

    No Known Activations