© 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. 22982
    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
    that
    -0.13
    	that
    -0.12
    ที่
    -0.12
     that
    -0.12
     જેને
    -0.11
     qui
    -0.11
     ที่
    -0.11
     THAT
    -0.11
     that'll
    -0.10
     οποίος
    -0.10
    POSITIVE LOGITS
     are
    0.22
     is
    0.19
     exists
    0.17
     occurs
    0.16
     were
    0.16
     существуют
    0.16
     happens
    0.15
     existe
    0.15
     существует
    0.15
     используются
    0.15
    Activations Density 0.101%

    No Known Activations