© 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. 11-RESID-POST-AA
    11. 71429
    Prev
    Next
    INDEX
    Explanations

    Definitions and broad terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .must
    -0.08
     Midi
    -0.08
    .should
    -0.08
     batean
    -0.08
     Acht
    -0.08
     Mad
    -0.08
     Madness
    -0.08
     يريد
    -0.08
     Nunca
    -0.08
    .restore
    -0.08
    POSITIVE LOGITS
     encompass
    0.13
     encompasses
    0.11
     encompassing
    0.11
    涵
    0.11
     broadly
    0.10
    ，包括
    0.09
    简称
    0.09
     umfasst
    0.09
    包括
    0.09
     excluding
    0.09
    Activations Density 0.123%

    No Known Activations