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. 43362
    Prev
    Next
    INDEX
    Explanations

    Software and technology

    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
     agriculture
    -0.08
     ->
    -0.07
     Agricultural
    -0.07
     Farmers
    -0.07
     कृषि
    -0.07
     nae
    -0.07
    ~↵↵
    -0.07
    ுள்ள
    -0.07
     دهید
    -0.07
     agricultural
    -0.07
    POSITIVE LOGITS
    との
    0.09
     integrations
    0.09
     compatible
    0.09
     Compatible
    0.08
     fico
    0.08
     surrogate
    0.08
     интег
    0.08
     talab
    0.08
     sor
    0.08
    hic
    0.08
    Activations Density 0.112%

    No Known Activations