© 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. 22775
    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
    νοντας
    -0.10
     eraill
    -0.09
     cheiro
    -0.09
    ayət
    -0.09
     المسلحة
    -0.09
    арып
    -0.09
     azar
    -0.09
    имер
    -0.09
    Firewall
    -0.09
    ваются
    -0.09
    POSITIVE LOGITS
    icity
    0.15
     length
    0.12
    length
    0.12
    Length
    0.12
    ical
    0.11
    _length
    0.11
    -length
    0.11
     Length
    0.11
    lessness
    0.10
    oidal
    0.10
    Activations Density 0.006%

    No Known Activations