© 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. 79283
    Prev
    Next
    INDEX
    Explanations

    restaurant/cafe reviews

    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
    ß
    -0.09
    SQL
    -0.08
     rigorous
    -0.08
     teraz
    -0.08
    objective
    -0.08
     elettron
    -0.08
    (callback
    -0.07
     बाध
    -0.07
    _consum
    -0.07
     eku
    -0.07
    POSITIVE LOGITS
     London
    0.09
    会上
    0.09
     разделе
    0.08
     районе
    0.08
     유명
    0.08
     aboard
    0.08
     Boulevard
    0.08
    London
    0.08
     곳
    0.08
     tucked
    0.08
    Activations Density 0.026%

    No Known Activations