© 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. 70482
    Prev
    Next
    INDEX
    Explanations

    Session

    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
    90
    -0.09
     locus
    -0.08
     loci
    -0.07
     Grass
    -0.07
    章
    -0.07
     с
    -0.07
    -0.07
     crypt
    -0.07
     drill
    -0.07
    NAV
    -0.07
    POSITIVE LOGITS
     बन
    0.08
     �
    0.08
     kesehatan
    0.08
     lubric
    0.08
     Kuba
    0.08
    Rom
    0.08
     lubricant
    0.08
    .Home
    0.08
     બનાવ
    0.08
    pecial
    0.08
    Activations Density 0.001%
    No Known Activations