© 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. 1495
    Prev
    Next
    INDEX
    Explanations

    N

    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
     combust
    -0.07
    (([
    -0.07
     beteiligt
    -0.07
    सू
    -0.07
     wield
    -0.07
    _department
    -0.07
    Ciudad
    -0.07
    <?>)
    -0.07
     tav
    -0.07
    (renderer
    -0.07
    POSITIVE LOGITS
    .Ignore
    0.08
     BW
    0.08
    .poll
    0.08
    duino
    0.08
     Amb
    0.08
     Pac
    0.08
    hew
    0.08
     Grass
    0.08
    .As
    0.07
     Mole
    0.07
    Activations Density 0.000%

    No Known Activations