© 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. 2498
    Prev
    Next
    INDEX
    Explanations

    different

    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
     стиль
    -0.08
     Mot
    -0.07
     ог
    -0.07
    abber
    -0.07
    ,font
    -0.07
     jaw
    -0.07
     envelope
    -0.07
    Hans
    -0.07
    manship
    -0.07
     VP
    -0.07
    POSITIVE LOGITS
     SER
    0.08
     Lyc
    0.08
     السي
    0.08
     STF
    0.08
     Rican
    0.08
    SER
    0.07
    CTION
    0.07
     අව
    0.07
    akad
    0.07
     લઈને
    0.07
    Activations Density 0.020%

    No Known Activations