© 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. 2768
    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
     técnica
    -0.08
    技
    -0.07
    qty
    -0.07
     Tat
    -0.07
    favicon
    -0.07
    Tutorial
    -0.07
    фт
    -0.07
     tecnica
    -0.07
    Law
    -0.07
     perennial
    -0.07
    POSITIVE LOGITS
    (opts
    0.08
     opio
    0.08
     Et
    0.08
     ranger
    0.07
     wagers
    0.07
     мыш
    0.07
     wager
    0.07
     Edwards
    0.07
     sonido
    0.07
    _beta
    0.07
    Activations Density 0.003%

    No Known Activations