© 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. 23-RESID-POST-AA
    11. 52006
    Prev
    Next
    INDEX
    Explanations

    JSP

    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
     Ethereum
    -0.09
    .ethereum
    -0.08
     Seri
    -0.08
    Ethereum
    -0.08
    \Seeder
    -0.08
     Amm
    -0.08
     notch
    -0.07
    .grpc
    -0.07
    Cursor
    -0.07
     punct
    -0.07
    POSITIVE LOGITS
     JSP
    0.23
    jspx
    0.21
     JST
    0.20
     jsp
    0.19
    .tagext
    0.19
    jsp
    0.18
    .jsp
    0.17
     thyme
    0.17
     Thy
    0.16
    thy
    0.15
    Activations Density 0.007%

    No Known Activations