© 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. 63882
    Prev
    Next
    INDEX
    Explanations

    ый

    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
    ameni
    -0.08
     nationality
    -0.08
     incredibly
    -0.07
     exceedingly
    -0.07
     once
    -0.07
    everyone
    -0.07
    Signup
    -0.07
     intensely
    -0.07
     extremely
    -0.07
    _i
    -0.07
    POSITIVE LOGITS
    挑战
    0.09
     Maver
    0.09
     adventure
    0.08
     vogue
    0.08
     challenge
    0.08
    (detail
    0.08
     Hollywood
    0.08
     thriller
    0.08
     candy
    0.08
     Challenge
    0.08
    Activations Density 0.008%

    No Known Activations