© 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. 49057
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anor
    -0.09
    haf
    -0.08
     Vielleicht
    -0.08
     onnist
    -0.08
    ocl
    -0.08
     Avalanche
    -0.08
     Palestinian
    -0.08
    /message
    -0.08
     Midlands
    -0.08
     glacier
    -0.08
    POSITIVE LOGITS
    0.10
     క్ర
    0.09
    ตั้ง
    0.09
     principalement
    0.09
     généralement
    0.09
     principaux
    0.09
    主要
    0.08
     ตั้ง
    0.08
    საქართველ
    0.08
     ക്ര
    0.08
    Activations Density 0.004%

    No Known Activations