© 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. 22786
    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
     returned
    -0.09
    Answer
    -0.09
    ({
    -0.09
     requester
    -0.09
     asker
    -0.09
     if
    -0.08
    �
    -0.08
     answer
    -0.08
    ={
    -0.08
     =
    -0.08
    POSITIVE LOGITS
     discusses
    0.22
     discussing
    0.20
     discussions
    0.19
    讨论
    0.18
     discuss
    0.17
    Discuss
    0.17
     चर्चा
    0.17
     Discuss
    0.16
     আলোচনা
    0.16
     discussão
    0.16
    Activations Density 0.071%

    No Known Activations