© 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. 44627
    Prev
    Next
    INDEX
    Explanations

    The, Answer

    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
    ijn
    -0.08
     രാജ്യ
    -0.08
     Rabbit
    -0.07
     Cycling
    -0.07
    ereço
    -0.07
     probar
    -0.07
    ्कार
    -0.07
    เม
    -0.07
     ict
    -0.07
     kraj
    -0.07
    POSITIVE LOGITS
    百科
    0.09
     yakın
    0.08
    热门
    0.08
     legisl
    0.08
     legislation
    0.07
    enua
    0.07
     популярных
    0.07
    :def
    0.07
    )section
    0.07
     lawsuits
    0.07
    Activations Density 0.004%

    No Known Activations