© 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. 112328
    Prev
    Next
    INDEX
    Explanations

    compatibility and devices

    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
    حث
    -0.09
    ня
    -0.08
     مس
    -0.08
    [arr
    -0.07
    ظيم
    -0.07
    сор
    -0.07
     تعلم
    -0.07
     ня
    -0.07
    革命
    -0.07
     alde
    -0.07
    POSITIVE LOGITS
     Tested
    0.12
     getestet
    0.10
     tested
    0.10
     testers
    0.09
    Testing
    0.09
     getest
    0.09
     kompat
    0.09
     Testing
    0.09
    Versions
    0.09
    _versions
    0.09
    Activations Density 0.020%

    No Known Activations