© 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. 26215
    Prev
    Next
    INDEX
    Explanations

    zano

    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
    odo
    -0.08
    :image
    -0.08
     যোগাযোগ
    -0.08
    (of
    -0.08
     assimil
    -0.07
     cit
    -0.07
    íð
    -0.07
     STR
    -0.07
    Assim
    -0.07
     cellules
    -0.07
    POSITIVE LOGITS
     quake
    0.08
     naf
    0.08
     Erfahrung
    0.08
     unary
    0.07
    _theme
    0.07
    staben
    0.07
     Нет
    0.07
     LU
    0.07
    爆
    0.07
     Prescription
    0.07
    Activations Density 0.001%

    No Known Activations