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. 58544
    Prev
    Next
    INDEX
    Explanations

    finance and investment

    np_max-act · gemini-2.0-flash

    attends from position-indicating tokens, such as numbers or ordinals, to nearby context or descriptors of those positions.

    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
     propre
    -0.09
    rp
    -0.08
     unified
    -0.08
     punctuation
    -0.07
     rp
    -0.07
    rpc
    -0.07
     ocupado
    -0.07
    Bog
    -0.07
     secretion
    -0.07
     aps
    -0.07
    POSITIVE LOGITS
    每日
    0.10
     Designed
    0.09
     günlük
    0.09
     दैनिक
    0.09
     onderwerpen
    0.09
    報
    0.09
     DAILY
    0.09
     هدف
    0.09
    .daily
    0.09
    每天
    0.08
    Activations Density 0.006%

    No Known Activations