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. 111703
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
    ếp
    -0.09
     inspecting
    -0.08
    FOLLOW
    -0.08
     отмен
    -0.08
     rude
    -0.08
     grief
    -0.08
    Subscribe
    -0.08
     читать
    -0.08
    ći
    -0.08
    Inspection
    -0.08
    POSITIVE LOGITS
     symmetrical
    0.10
     symmetric
    0.09
     klasik
    0.09
     guud
    0.09
     univer
    0.09
     maksimum
    0.09
     biznes
    0.08
     SWOT
    0.08
     Optimal
    0.08
     maximize
    0.08
    Activations Density 0.061%

    No Known Activations