© 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. 16703
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ↵
    -0.08
     šal
    -0.08
    .
    -0.08
    .O
    -0.07
     सुनिश्चित
    -0.07
    .↵↵
    -0.07
     by
    -0.07
     أو
    -0.07
    ;
    -0.07
     był
    -0.07
    POSITIVE LOGITS
     respectively
    0.11
     қатарлиқ
    0.11
     дегән
    0.10
    ропа
    0.10
     എന്നീ
    0.10
    分别
    0.10
    верж
    0.10
    ләрниң
    0.10
    лардин
    0.09
    ларниң
    0.09
    Activations Density 0.011%

    No Known Activations