© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
     Mot
    -0.08
    ara
    -0.08
    ansen
    -0.08
    (';
    -0.08
     annotated
    -0.07
    kripsi
    -0.07
    (DE
    -0.07
     iki
    -0.07
    ([],
    -0.07
    OTES
    -0.07
    POSITIVE LOGITS
    utc
    0.08
     pretty
    0.08
     Cooper
    0.08
     opiskel
    0.08
     automobil
    0.07
    赶
    0.07
     unimagin
    0.07
    भी
    0.07
     суб
    0.07
     городе
    0.07
    Activations Density 0.000%

    No Known Activations