Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 106037
    Prev
    Next
    INDEX
    Explanations

    taxes on the rich

    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
     chewy
    -0.08
     brittle
    -0.08
     мок
    -0.08
     ponto
    -0.08
     Deaf
    -0.08
    夹
    -0.07
    步
    -0.07
     visually
    -0.07
    �
    -0.07
     toget
    -0.07
    POSITIVE LOGITS
     billionaire
    0.10
     incomes
    0.09
     वर
    0.09
     பெரிய
    0.09
    _income
    0.08
     polynomial
    0.08
     elites
    0.08
     percentile
    0.08
     supremacy
    0.08
     prises
    0.07
    Activations Density 0.012%

    No Known Activations