Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 75
    Prev
    Next
    INDEX
    Explanations

    scientific/medical abstracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myös
    -0.09
     также
    -0.08
     и
    -0.08
     và
    -0.08
     також
    -0.08
     various
    -0.08
     also
    -0.08
    вычай
    -0.08
     außerdem
    -0.08
     Democratic
    -0.08
    POSITIVE LOGITS
    —a
    0.11
    —which
    0.10
    ,这是
    0.10
     ซึ่ง
    0.10
    经典
    0.10
     (**
    0.09
    라는
    0.09
    这是
    0.09
     reliably
    0.08
    0.08
    Activations Density 0.002%

    No Known Activations