© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 111289
    Prev
    Next
    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avyo
    -0.09
     drone
    -0.08
     scuba
    -0.08
     petroleum
    -0.08
    ，如
    -0.07
    产品
    -0.07
    ，实现
    -0.07
    طوان
    -0.07
    aqu
    -0.07
     cyl
    -0.07
    POSITIVE LOGITS
     ndetse
    0.09
     ngunit
    0.09
     complemented
    0.09
     وكذلك
    0.09
     initially
    0.09
    ırken
    0.09
     ولكن
    0.09
     కానీ
    0.08
     salted
    0.08
    そして
    0.08
    Activations Density 0.487%

    No Known Activations