© 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. 18243
    Prev
    Next
    INDEX
    Explanations

    unreal

    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
    이번
    -0.10
    ҳи
    -0.10
     더욱
    -0.09
    лоо
    -0.09
    もっと
    -0.09
     самое
    -0.09
     anois
    -0.09
     toinen
    -0.09
     이번
    -0.09
     הראשונה
    -0.09
    POSITIVE LOGITS
    licable
    0.10
    formed
    0.09
    ified
    0.09
    listed
    0.09
    ated
    0.09
    essary
    0.09
    scribed
    0.09
    izable
    0.09
    anceled
    0.09
    ued
    0.09
    Activations Density 0.003%

    No Known Activations