© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 47528
    Prev
    Next
    INDEX
    Explanations

    diode

    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
    മുള്ള
    -0.09
    खी
    -0.08
     believing
    -0.08
     matlab
    -0.08
     awk
    -0.08
     believe
    -0.08
     belief
    -0.07
    ख
    -0.07
     varias
    -0.07
    _FORE
    -0.07
    POSITIVE LOGITS
     للت
    0.08
     Bri
    0.07
    Completion
    0.07
    926
    0.07
    Rice
    0.07
     Roche
    0.07
     Amal
    0.07
     Sonia
    0.07
     pozi
    0.07
     É
    0.07
    Activations Density 0.001%

    No Known Activations