© 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. 23-RESID-POST-AA
    11. 51617
    Prev
    Next
    INDEX
    Explanations

    Ancient Chinese bronze artifacts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rock
    -0.08
     broccoli
    -0.08
     starch
    -0.07
     opinions
    -0.07
    oeira
    -0.07
     fern
    -0.07
    kein
    -0.07
     orange
    -0.07
     concede
    -0.07
    UA
    -0.07
    POSITIVE LOGITS
    领奖
    0.10
     LIABLE
    0.09
    司
    0.08
     beverage
    0.08
    (lib
    0.08
     člov
    0.08
     mairie
    0.08
     histogram
    0.08
     mapper
    0.08
     гіст
    0.08
    Activations Density 0.002%

    No Known Activations