© 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. 110501
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Jeep
    -0.08
     Diva
    -0.08
     ovar
    -0.08
     دیج
    -0.08
     Pune
    -0.08
     ورو
    -0.08
     Aug
    -0.07
    .unlock
    -0.07
    (Optional
    -0.07
     togg
    -0.07
    POSITIVE LOGITS
     observations
    0.09
    성
    0.08
    仕様
    0.08
     exercised
    0.07
    usy
    0.07
     documents
    0.07
     BIS
    0.07
    许
    0.07
     Brooks
    0.07
    ીસ
    0.07
    Activations Density 0.001%

    No Known Activations