© 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. 23-RESID-POST-AA
    11. 5488
    Prev
    Next
    INDEX
    Explanations

    sectors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اتها
    -0.09
    cules
    -0.08
     Ai
    -0.08
    ?,
    -0.07
    unye
    -0.07
    �
    -0.07
    .avg
    -0.07
     شوې
    -0.07
    ?)
    -0.07
    ательной
    -0.07
    POSITIVE LOGITS
     sektor
    0.11
    部门
    0.10
     sekt
    0.09
     القطاع
    0.09
     निजी
    0.09
     settore
    0.09
    私人
    0.09
     sektör
    0.08
    対
    0.08
    _private
    0.08
    Activations Density 0.001%

    No Known Activations