© 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. 112602
    Prev
    Next
    INDEX
    Explanations

    improved healthcare and lifespan

    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
    \
    -0.08
     negócios
    -0.08
     negocio
    -0.08
     negocios
    -0.07
     Francisco
    -0.07
     Valenc
    -0.07
     задан
    -0.07
     rued
    -0.07
    Biz
    -0.07
    .neg
    -0.07
    POSITIVE LOGITS
    越来越
    0.10
     désormais
    0.09
     mittlerweile
    0.09
     cured
    0.09
     curing
    0.09
     increasingly
    0.09
     artık
    0.09
     Stabil
    0.09
     moderne
    0.09
     modernes
    0.09
    Activations Density 0.010%

    No Known Activations