© 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. 21110
    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
    confidence
    -0.08
    ленного
    -0.08
     pleasure
    -0.08
    urgery
    -0.07
     progresses
    -0.07
    .qu
    -0.07
     desserts
    -0.07
     (!(
    -0.07
     manipulating
    -0.07
    /png
    -0.07
    POSITIVE LOGITS
     primeras
    0.10
     simplemente
    0.10
     basic
    0.10
     premye
    0.09
     első
    0.09
     básica
    0.09
     simplesmente
    0.09
    .first
    0.09
     simplement
    0.09
     முதல்
    0.09
    Activations Density 0.080%

    No Known Activations