© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20202
    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
    —the
    -0.09
    ($('.
    -0.08
    application
    -0.08
    varer
    -0.08
    producto
    -0.08
     KA
    -0.07
     והמ
    -0.07
    —a
    -0.07
    VP
    -0.07
     Аф
    -0.07
    POSITIVE LOGITS
    /oder
    0.10
    &nbsp
    0.10
     README
    0.10
     nameof
    0.09
     ~/.
    0.09
     \<
    0.09
     ./
    0.09
    ,omitempty
    0.09
     Optional
    0.09
     fugiat
    0.09
    Activations Density 0.003%

    No Known Activations