© 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. 21732
    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
     orthodont
    -0.13
    バッグ
    -0.11
     kleding
    -0.10
     Kleid
    -0.10
     USPS
    -0.10
     Nike
    -0.10
     eyew
    -0.10
     handset
    -0.10
     shoe
    -0.10
    制服
    -0.10
    POSITIVE LOGITS
     hepat
    0.31
     hepatic
    0.30
     liver
    0.30
     hepatitis
    0.29
     Liver
    0.25
     Hep
    0.25
     hep
    0.20
     печени
    0.19
    hep
    0.17
     bili
    0.17
    Activations Density 0.011%

    No Known Activations