© 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. 45747
    Prev
    Next
    INDEX
    Explanations

    pumpkin seeds

    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
     fronts
    -0.08
     front
    -0.08
    frontend
    -0.07
    _FRONT
    -0.07
    -0.07
    Front
    -0.07
    _REL
    -0.07
    _SUM
    -0.07
     previously
    -0.07
    -0.07
    POSITIVE LOGITS
     earrings
    0.09
     Earrings
    0.08
     (…)
    0.08
     ofertas
    0.08
    嘿
    0.08
     preparados
    0.08
     regularmente
    0.08
    .auth
    0.08
     obsess
    0.08
     potreb
    0.08
    Activations Density 0.001%
    No Known Activations