© 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. 129136
    Prev
    Next
    INDEX
    Explanations

    iceps

    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
     receb
    -0.08
     success
    -0.07
    炉
    -0.07
     unw
    -0.07
     layer
    -0.07
     preliminary
    -0.07
    enir
    -0.07
    undance
    -0.07
    -coming
    -0.07
     biotechnology
    -0.07
    POSITIVE LOGITS
     Hass
    0.09
    cv
    0.09
     tire
    0.08
     playa
    0.08
    	cv
    0.08
     cv
    0.08
     мышцы
    0.08
    servo
    0.08
     fis
    0.08
     выбора
    0.08
    Activations Density 0.001%

    No Known Activations