© 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 EvalsExportsinterp-engineNEWAPI 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. 21762
    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
    ruby
    -0.08
     berasal
    -0.08
    spiracy
    -0.08
     merupakan
    -0.08
    negative
    -0.08
    <java
    -0.08
    prakt
    -0.08
    save
    -0.08
     cuma
    -0.08
     JNICALL
    -0.07
    POSITIVE LOGITS
     can
    0.11
    0.09
     TOTAL
    0.08
     might
    0.08
    /uploads
    0.07
     маршрут
    0.07
     may
    0.07
     could
    0.07
     transfers
    0.07
     durée
    0.07
    Activations Density 0.005%
    No Known Activations