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. 111803
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     trio
    -0.08
     macro
    -0.08
    awesome
    -0.08
     awesome
    -0.07
    -lang
    -0.07
    Awesome
    -0.07
    认可
    -0.07
     pair
    -0.07
    ison
    -0.07
    _lang
    -0.07
    POSITIVE LOGITS
     vielmehr
    0.12
     बल्कि
    0.11
     بلکه
    0.10
     بلکہ
    0.09
     actively
    0.08
    어서
    0.08
     sondern
    0.08
     Zum
    0.08
    0.08
     encompass
    0.08
    Activations Density 0.041%

    No Known Activations