© 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. 11-RESID-POST-AA
    11. 110328
    Prev
    Next
    INDEX
    Explanations

    wet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meter
    -0.08
     feeding
    -0.08
     FE
    -0.07
    ền
    -0.07
    -0.07
    bu
    -0.07
    łoż
    -0.07
    ke
    -0.07
    _FE
    -0.07
     missing
    -0.07
    POSITIVE LOGITS
     aanleiding
    0.09
     pneus
    0.09
    ACHE
    0.09
     MAIS
    0.08
     stunned
    0.08
     vznik
    0.08
     Cassidy
    0.08
    .Paths
    0.08
     repaired
    0.08
     akibat
    0.08
    Activations Density 0.011%
    No Known Activations