© 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. 11-RESID-POST-AA
    11. 45643
    Prev
    Next
    INDEX
    Explanations

    maximum, minimum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cei
    -0.08
    аныя
    -0.08
    简单
    -0.08
     другим
    -0.07
    опр
    -0.07
     зр
    -0.07
     phổ
    -0.07
     задерж
    -0.07
    анией
    -0.07
     đơn
    -0.07
    POSITIVE LOGITS
     maximizing
    0.08
     achievable
    0.08
     calculation
    0.08
     Comprar
    0.08
     significativamente
    0.08
     configurations
    0.08
     combination
    0.07
     substantially
    0.07
    	config
    0.07
    ibile
    0.07
    Activations Density 0.037%

    No Known Activations