© 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. 25061
    Prev
    Next
    INDEX
    Explanations

    than

    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
     eenvoudige
    -0.08
    	results
    -0.08
     superficial
    -0.08
    -0.08
     calmly
    -0.08
    地产
    -0.08
     наиболее
    -0.08
     zwar
    -0.08
    最低
    -0.07
     поверхности
    -0.07
    POSITIVE LOGITS
     Hospital
    0.08
     ואין
    0.08
    otok
    0.08
     endless
    0.08
     pitkä
    0.08
     હોસ્પિટલ
    0.07
    omeza
    0.07
     Reino
    0.07
     turi
    0.07
     necesariamente
    0.07
    Activations Density 0.016%
    No Known Activations