© 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. 22899
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ндекс
    -0.09
    España
    -0.09
     качество
    -0.09
    Italian
    -0.09
    ुक्त
    -0.09
    �
    -0.09
    ත්ත
    -0.09
    Absolutely
    -0.08
    Ɛ
    -0.08
    Выс
    -0.08
    POSITIVE LOGITS
     него
    0.16
     каждой
    0.14
     каждого
    0.13
     нее
    0.13
     неё
    0.13
     этих
    0.12
     них
    0.12
    казыва
    0.12
     этой
    0.11
     процесса
    0.11
    Activations Density 0.003%

    No Known Activations