© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48018
    Prev
    Next
    INDEX
    Explanations

    price discrimination and bias

    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
     achar
    -0.09
     swap
    -0.09
     Swap
    -0.09
     intercambio
    -0.08
    Swap
    -0.08
    Exchange
    -0.08
     exchange
    -0.08
    iknya
    -0.08
     exchanged
    -0.08
     Mez
    -0.08
    POSITIVE LOGITS
     sexes
    0.09
    별
    0.08
     unterschiedliche
    0.08
     конц
    0.08
     cann
    0.08
     разные
    0.08
     الجوية
    0.08
    -paid
    0.08
     प्रति
    0.08
    циа
    0.07
    Activations Density 0.007%

    No Known Activations