© 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. 91518
    Prev
    Next
    INDEX
    Explanations

    book, series

    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
     FEMA
    -0.08
     physi
    -0.07
    tested
    -0.07
    ativas
    -0.07
     achievements
    -0.07
    staat
    -0.07
     Tested
    -0.07
     municipality
    -0.07
     achievable
    -0.07
     phys
    -0.07
    POSITIVE LOGITS
     اوږ
    0.09
    Ca
    0.08
    	remove
    0.08
     چنین
    0.08
     ښک
    0.08
    Excerpt
    0.08
     jab
    0.08
    ORPG
    0.08
    ξαν
    0.07
    龍
    0.07
    Activations Density 0.030%

    No Known Activations