© 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. 21070
    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
     pesky
    -0.11
     killexams
    -0.10
     flavorful
    -0.10
     yummy
    -0.10
     picky
    -0.10
    秘籍
    -0.10
    老司机
    -0.10
    靠谱
    -0.10
     Grammarly
    -0.10
    客服
    -0.10
    POSITIVE LOGITS
     sculpture
    0.20
     sculptures
    0.20
     작품
    0.16
     collage
    0.16
     avant
    0.16
     Sculpture
    0.16
     expér
    0.16
    作品
    0.15
     experimental
    0.15
     kunstenaars
    0.15
    Activations Density 0.170%

    No Known Activations