© 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. 113540
    Prev
    Next
    INDEX
    Explanations

    sans

    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
    cknowled
    -0.09
     সূ
    -0.08
    /legal
    -0.08
    asio
    -0.08
     cust
    -0.08
     Distr
    -0.08
     الأس
    -0.08
     উপল
    -0.08
    psilon
    -0.07
     deed
    -0.07
    POSITIVE LOGITS
    -serif
    0.08
    0.08
     rod
    0.07
     doubt
    0.07
     FR
    0.07
     रह
    0.07
     regard
    0.07
     Hig
    0.07
     Vai
    0.07
     VC
    0.07
    Activations Density 0.004%
    No Known Activations