© 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. 19-RESID-POST-AA
    11. 21563
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arsuaq
    -0.08
    极速
    -0.08
     restructure
    -0.08
    不卡
    -0.07
     الجولة
    -0.07
    _Update
    -0.07
     ஜன
    -0.07
     DATABASE
    -0.07
     inplace
    -0.07
     अपडेट
    -0.07
    POSITIVE LOGITS
     symbolism
    0.42
     symbolic
    0.32
     символ
    0.31
     simbol
    0.30
    Symbol
    0.29
     Symbol
    0.29
     symbol
    0.29
     symbolizes
    0.28
     symbols
    0.28
     symbolize
    0.28
    Activations Density 0.093%

    No Known Activations