© 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. 95856
    Prev
    Next
    INDEX
    Explanations

    ري

    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
    esthetic
    -0.08
     Nor
    -0.08
     Northwestern
    -0.08
    _callable
    -0.08
    weni
    -0.08
    MP
    -0.07
     ach
    -0.07
     ekspl
    -0.07
     Unidos
    -0.07
     Laguna
    -0.07
    POSITIVE LOGITS
     Syr
    0.08
     Crus
    0.08
    sticks
    0.07
    刷
    0.07
    assim
    0.07
     Tal
    0.07
    306
    0.07
     Soph
    0.07
    Tal
    0.07
     rehearsal
    0.07
    Activations Density 0.008%

    No Known Activations