© 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. 2517
    Prev
    Next
    INDEX
    Explanations

    же

    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
     habitation
    -0.07
     Sputnik
    -0.07
    (sr
    -0.07
    ूम
    -0.07
    .vn
    -0.07
    .us
    -0.07
     dole
    -0.07
    kiem
    -0.07
     prides
    -0.07
     crisis
    -0.07
    POSITIVE LOGITS
    apos
    0.08
    inding
    0.07
     print
    0.07
     kund
    0.07
    AVED
    0.07
    ##_
    0.07
     severely
    0.07
    -(
    0.07
    587
    0.07
    144
    0.07
    Activations Density 0.000%

    No Known Activations