© 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. 77913
    Prev
    Next
    INDEX
    Explanations

    Asian food/languages

    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
     plush
    -0.09
     plak
    -0.09
    estial
    -0.09
    ритан
    -0.09
     Investors
    -0.08
    urso
    -0.08
     Belly
    -0.08
     заявки
    -0.08
     бір
    -0.08
     aborto
    -0.08
    POSITIVE LOGITS
    stations
    0.08
    .channel
    0.08
    Android
    0.08
    当天
    0.08
    오늘
    0.07
     Commod
    0.07
     清
    0.07
     both
    0.07
     तर
    0.07
     اليومية
    0.07
    Activations Density 0.005%

    No Known Activations