© 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. 91491
    Prev
    Next
    INDEX
    Explanations

    kitchen, cooking

    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
    ాది
    -0.09
     secrecy
    -0.08
    имен
    -0.08
    赔率
    -0.07
     hedef
    -0.07
     гал
    -0.07
     వ్య
    -0.07
     nommé
    -0.07
     piem
    -0.07
     bahis
    -0.07
    POSITIVE LOGITS
     kitchenette
    0.10
     kitchen
    0.09
     gask
    0.09
     programmable
    0.08
     Electricity
    0.08
     electricity
    0.08
    Kitchen
    0.08
     suic
    0.08
     suicidal
    0.08
     кух
    0.08
    Activations Density 0.030%

    No Known Activations