© 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. 22968
    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
     πό
    -0.08
    imani
    -0.08
    ãng
    -0.07
    érature
    -0.07
    बे
    -0.07
     pô
    -0.07
     izol
    -0.07
    enade
    -0.07
    итета
    -0.07
     pü
    -0.07
    POSITIVE LOGITS
    填写
    0.43
     preencher
    0.39
     preench
    0.37
     remplir
    0.37
     заполн
    0.36
    填
    0.35
     filling
    0.34
     fill
    0.34
     Fill
    0.34
     llenar
    0.34
    Activations Density 0.077%

    No Known Activations