© 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 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. 64015
    Prev
    Next
    INDEX
    Explanations

    compelling

    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
     legt
    -0.09
    YM
    -0.08
    כן
    -0.07
    outine
    -0.07
     Hir
    -0.07
     Francisco
    -0.07
     விட்ட
    -0.07
    session
    -0.07
     న
    -0.07
     memb
    -0.07
    POSITIVE LOGITS
     compelling
    0.10
     genug
    0.08
    isos
    0.08
    VC
    0.08
     chimney
    0.08
    صة
    0.08
    Driven
    0.07
    matic
    0.07
     driven
    0.07
     coated
    0.07
    Activations Density 0.004%

    No Known Activations