© 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. 22818
    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
     illetve
    -0.08
     arist
    -0.08
    olim
    -0.07
     [{
    -0.07
     případě
    -0.07
    nius
    -0.07
     oblasti
    -0.07
    Instances
    -0.07
     arrêté
    -0.07
    ncia
    -0.07
    POSITIVE LOGITS
    (↵
    0.15
    _merge
    0.15
    _keys
    0.13
    (↵↵
    0.13
    _replace
    0.13
    _key
    0.12
     (↵
    0.12
    _reduce
    0.12
    _values
    0.12
    _column
    0.12
    Activations Density 0.001%

    No Known Activations