© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 65595
    Prev
    Next
    INDEX
    Explanations

    rhombus properties

    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
     nach
    -0.09
     extravag
    -0.08
     nas
    -0.07
     Gog
    -0.07
     gamm
    -0.07
     quinta
    -0.07
     vamp
    -0.07
    ANNOT
    -0.07
     portable
    -0.07
     ultras
    -0.07
    POSITIVE LOGITS
    (rate
    0.08
    licate
    0.08
    चारी
    0.07
    constraints
    0.07
     सहज
    0.07
     clen
    0.07
     iji
    0.07
    meric
    0.07
    梯
    0.07
    ====
    0.07
    Activations Density 0.002%

    No Known Activations