© 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 EvalsExportsAPI 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. 112641
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     AW
    -0.09
     ڪم
    -0.08
     whakah
    -0.08
    همة
    -0.08
    ្វើ
    -0.08
     يقوم
    -0.08
    יכון
    -0.08
    บาย
    -0.07
    ದ್ಯ
    -0.07
    ದು
    -0.07
    POSITIVE LOGITS
     és
    0.08
    oroč
    0.07
     পর্যন্ত
    0.07
     siap
    0.07
     percaya
    0.07
     stimulate
    0.07
     mob
    0.07
    raisal
    0.07
     shoppers
    0.07
    TOTAL
    0.07
    Activations Density 0.016%

    No Known Activations