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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53863
    Prev
    Next
    INDEX
    Explanations

    Economics, GDP

    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
     nearly
    -0.09
     almost
    -0.08
    Wifi
    -0.08
    .Dict
    -0.07
     prüfen
    -0.07
    almost
    -0.07
     quase
    -0.07
     psychology
    -0.07
    Almost
    -0.07
     psychologie
    -0.07
    POSITIVE LOGITS
     Prices
    0.09
     �
    0.09
    ڼه
    0.08
     prices
    0.08
     versione
    0.08
     fashioned
    0.08
     Scheme
    0.08
     moda
    0.08
    Prices
    0.08
    .updated
    0.08
    Activations Density 0.004%

    No Known Activations