© 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. 22843
    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
     itself
    -0.10
    irse
    -0.10
     its
    -0.10
     করছে
    -0.10
     ತನ್ನ
    -0.10
     ponerse
    -0.10
     kanyang
    -0.10
     שלהם
    -0.10
     dirinya
    -0.09
     తమ
    -0.09
    POSITIVE LOGITS
    ’m
    0.26
     myself
    0.23
     люблю
    0.23
     am
    0.22
     माझ
    0.19
     mezelf
    0.19
     എന്റെ
    0.19
     મારા
    0.19
     хочу
    0.19
     నా
    0.19
    Activations Density 0.068%

    No Known Activations