© 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. 23052
    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
     sois
    -0.09
    _'+
    -0.09
    _'
    -0.08
     faktiskt
    -0.08
    ‌తో
    -0.08
     effectivement
    -0.08
     некоторых
    -0.08
    'aide
    -0.08
     réellement
    -0.07
     만든
    -0.07
    POSITIVE LOGITS
     occurs
    0.24
     happens
    0.22
     requires
    0.21
     happen
    0.19
     occur
    0.18
     ocurre
    0.17
     ঘটে
    0.17
     happening
    0.17
     occurring
    0.17
     ocorre
    0.17
    Activations Density 0.017%

    No Known Activations