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. 15-RESID-POST-AA
    6. 18948
    Prev
    Next
    INDEX
    Explanations

    modernization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ([...
    -0.09
     daily
    -0.08
    據
    -0.08
     previamente
    -0.08
     недель
    -0.08
     namelijk
    -0.08
     eerder
    -0.08
    -nine
    -0.08
    atriz
    -0.08
     weekly
    -0.08
    POSITIVE LOGITS
     modernization
    0.12
    现代
    0.12
     الثورة
    0.12
     globalization
    0.11
     modern
    0.11
     neoliberal
    0.11
     현대
    0.11
     século
    0.11
     décadas
    0.10
    Modern
    0.10
    Activations Density 0.057%

    No Known Activations