© 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. 7-RESID-POST-AA
    11. 1365
    Prev
    Next
    INDEX
    Explanations

    NN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quo
    -0.09
     trolley
    -0.09
     livraison
    -0.08
     furnace
    -0.08
     поиска
    -0.08
     Tuk
    -0.08
     Apr
    -0.08
    QC
    -0.08
     convivencia
    -0.08
     wzgl
    -0.07
    POSITIVE LOGITS
     lace
    0.07
     Pearl
    0.07
     ಮುಂದ
    0.07
     который
    0.07
     Bass
    0.07
     komme
    0.07
     patterns
    0.07
     habitual
    0.07
    elt
    0.07
     котором
    0.07
    Activations Density 0.000%

    No Known Activations