© 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. 110489
    Prev
    Next
    INDEX
    Explanations

    conference

    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
    bac
    -0.07
     betekenis
    -0.07
     intelligent
    -0.07
     biomass
    -0.07
    Point
    -0.07
     punkt
    -0.07
     immersion
    -0.07
    astic
    -0.07
     thousand
    -0.07
     ba
    -0.07
    POSITIVE LOGITS
    ецеп
    0.10
    ское
    0.09
     councils
    0.09
     Finals
    0.09
     Ariana
    0.09
     Preliminary
    0.08
     Raw
    0.08
     counc
    0.08
     Мем
    0.08
     ლიგ
    0.08
    Activations Density 0.004%

    No Known Activations