© 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. 17994
    Prev
    Next
    INDEX
    Explanations

    name/description

    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
    Negative Logits
    Če
    -0.09
     רבות
    -0.09
     തീരുമ
    -0.09
     Hoewel
    -0.09
    artigen
    -0.09
     Dacă
    -0.08
     wọnyi
    -0.08
    เหล
    -0.08
     Sommige
    -0.08
    ffekt
    -0.08
    POSITIVE LOGITS
     कौन
    0.18
     name
    0.17
     location
    0.16
     hangi
    0.16
    名称
    0.16
     description
    0.16
     название
    0.16
     نوع
    0.15
     type
    0.15
     hvilke
    0.15
    Activations Density 0.087%

    No Known Activations