© 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. 1314
    Prev
    Next
    INDEX
    Explanations

    فيه

    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
     ACC
    -0.09
    ramer
    -0.08
    /res
    -0.08
    �
    -0.07
     مرتب
    -0.07
    UL
    -0.07
    Share
    -0.07
    LI
    -0.07
     Res
    -0.07
     cran
    -0.07
    POSITIVE LOGITS
     figur
    0.08
    ื้น
    0.08
    ชม
    0.08
     Grave
    0.08
    drive
    0.08
    ોચ
    0.07
     ફેર
    0.07
     Graves
    0.07
    Oz
    0.07
    -même
    0.07
    Activations Density 0.002%

    No Known Activations