© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18212
    Prev
    Next
    INDEX
    Explanations

    cholesterol

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Touch
    -0.09
     keyboards
    -0.09
     handwriting
    -0.09
    .keyboard
    -0.08
     pyn
    -0.08
    uart
    -0.08
    _keyboard
    -0.08
     Piano
    -0.08
    _mouse
    -0.08
     handwritten
    -0.08
    POSITIVE LOGITS
     cholesterol
    0.38
     colesterol
    0.34
     LDL
    0.29
     lipid
    0.29
     Chol
    0.26
    chol
    0.23
     HDL
    0.21
     chol
    0.20
    胆
    0.20
    esterol
    0.19
    Activations Density 0.011%

    No Known Activations