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. 102868
    Prev
    Next
    INDEX
    Explanations

    finance and investment

    np_max-act · gemini-2.0-flash

    attends from the start of a new text section marker to the start of each new text section.

    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
    .Message
    -0.08
     chore
    -0.07
     достоин
    -0.07
    Pers
    -0.07
    જબ
    -0.07
     christ
    -0.07
     legend
    -0.07
    Eventually
    -0.07
    Hopefully
    -0.07
    ocular
    -0.07
    POSITIVE LOGITS
     ETFs
    0.14
     proxies
    0.12
    proxy
    0.11
     ETF
    0.11
    股票
    0.11
     proxy
    0.11
    ETF
    0.10
     saham
    0.10
     股票
    0.10
     बजार
    0.09
    Activations Density 0.012%

    No Known Activations