© 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. 110921
    Prev
    Next
    INDEX
    Explanations

    nervous system

    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
     cards
    -0.09
     perks
    -0.08
     health
    -0.08
     appreciating
    -0.08
    -health
    -0.08
     simulations
    -0.08
     Cheers
    -0.07
    币
    -0.07
     Cards
    -0.07
    -0.07
    POSITIVE LOGITS
     нур
    0.09
    Satellite
    0.09
    ĝas
    0.08
    standen
    0.08
     leerling
    0.08
    tritt
    0.08
    다가
    0.08
    affig
    0.08
    generator
    0.08
     Schüler
    0.07
    Activations Density 0.003%
    No Known Activations