© 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. 23041
    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
     vielleicht
    -0.13
     kanske
    -0.13
     perhaps
    -0.12
    maybe
    -0.11
     talvez
    -0.11
     måske
    -0.11
     Vielleicht
    -0.11
    Vielleicht
    -0.11
     maybe
    -0.11
     It'll
    -0.10
    POSITIVE LOGITS
    进行了
    0.12
     हमने
    0.12
     fourteen
    0.11
     आम्ह
    0.11
     করেছি
    0.11
     fifteen
    0.10
    しました
    0.10
     Twenty
    0.10
     Thirty
    0.10
     wurden
    0.10
    Activations Density 0.010%

    No Known Activations