© 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. 64304
    Prev
    Next
    INDEX
    Explanations

    OLS models in python

    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
     prohib
    -0.08
    chtig
    -0.08
     Та
    -0.08
    ski
    -0.08
     Ret
    -0.07
     towers
    -0.07
     Tief
    -0.07
     Hardy
    -0.07
     Carlo
    -0.07
     Astra
    -0.07
    POSITIVE LOGITS
     narciss
    0.09
    zahlung
    0.08
     socially
    0.08
     något
    0.08
    SE
    0.07
     location
    0.07
     percentile
    0.07
     när
    0.07
     quantit
    0.07
     बैठे
    0.07
    Activations Density 0.001%

    No Known Activations