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. 65179
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    attends to publication dates from patent numbers.

    oai_attention-head · gpt-4oTriggered by @mlfinancebook
    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
    一句
    -0.09
     듯
    -0.08
     gente
    -0.08
    յուն
    -0.08
     metų
    -0.08
    笔
    -0.08
    teni
    -0.08
    uyen
    -0.08
     weyn
    -0.07
    mentions
    -0.07
    POSITIVE LOGITS
     arasında
    0.09
     ess
    0.09
     flesta
    0.08
     cuales
    0.08
     meisten
    0.08
     consecutive
    0.08
     fleste
    0.07
     усили
    0.07
     parts
    0.07
     §§
    0.07
    Activations Density 0.052%

    No Known Activations