© 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. 15-RESID-POST-AA
    11. 16486
    Prev
    Next
    INDEX
    Explanations

    a or the

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     collective
    -0.08
     διαφορε
    -0.08
     could
    -0.08
    利益
    -0.08
    大众
    -0.08
    重大
    -0.07
     varying
    -0.07
     bilim
    -0.07
    科技
    -0.07
    changing
    -0.07
    POSITIVE LOGITS
     screenplay
    0.13
     Screen
    0.09
     饰
    0.09
    .Screen
    0.09
     ನಿರ್ದೇಶ
    0.09
     Specifies
    0.09
    注明
    0.09
     SCREEN
    0.09
     पटक
    0.09
    0.08
    Activations Density 0.005%

    No Known Activations