© 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. 19352
    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
     będą
    -0.09
     比
    -0.09
     极速
    -0.09
     朋克
    -0.09
     色情
    -0.09
    ώντας
    -0.09
     赛车
    -0.09
    ální
    -0.09
     byli
    -0.09
    ेट
    -0.08
    POSITIVE LOGITS
    gharị
    0.10
    picked
    0.09
    tries
    0.09
    ffe
    0.08
    streng
    0.08
    chure
    0.08
    wig
    0.08
    veux
    0.08
    ver
    0.08
    breadcrumb
    0.08
    Activations Density 0.005%

    No Known Activations