© 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. 22747
    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
    Not in Any Lists

    No Comments

    Negative Logits
     اطلاعات
    -0.08
     information
    -0.07
     информация
    -0.07
     जानकारी
    -0.07
     RSS
    -0.07
     MAV
    -0.07
     complemented
    -0.07
     información
    -0.07
     RV
    -0.07
     CVS
    -0.07
    POSITIVE LOGITS
    -scenes
    0.08
    .‏
    0.08
    。：
    0.08
     combater
    0.08
    ক্ত
    0.08
     quân
    0.08
     defence
    0.08
     chống
    0.08
     Needs
    0.08
     snack
    0.08
    Activations Density 0.001%

    No Known Activations