© 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. 99714
    Prev
    Next
    INDEX
    Explanations

    theorems

    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
     biggest
    -0.08
     particularly
    -0.08
    ेरी
    -0.07
    ując
    -0.07
    ři
    -0.07
    _sr
    -0.07
    irty
    -0.07
    ł
    -0.07
    rị
    -0.07
    ємо
    -0.07
    POSITIVE LOGITS
     eher
    0.10
    ochemical
    0.09
    Rather
    0.08
    的是
    0.08
     außerhalb
    0.08
     बाह
    0.08
     Rather
    0.08
     unterschiedliche
    0.07
     rather
    0.07
     sexes
    0.07
    Activations Density 0.077%

    No Known Activations