© 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. 97560
    Prev
    Next
    INDEX
    Explanations

    Indigenous/First Nation People

    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
     cocina
    -0.09
     Cocina
    -0.08
     bins
    -0.08
     Foods
    -0.08
     foods
    -0.08
     procesu
    -0.08
     makanan
    -0.08
    ();↵↵↵
    -0.08
    τρα
    -0.08
     };↵↵↵
    -0.08
    POSITIVE LOGITS
    	back
    0.09
     back
    0.08
     Petr
    0.08
     oe
    0.08
    еть
    0.08
    دمت
    0.08
     Craig
    0.08
    .Back
    0.08
    _Back
    0.07
     backs
    0.07
    Activations Density 0.001%

    No Known Activations