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. 11-RESID-POST-AA
    6. 58566
    Prev
    Next
    INDEX
    Explanations

    nomination

    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
     trading
    -0.08
    (cookie
    -0.08
    caler
    -0.07
    zlich
    -0.07
    乗
    -0.07
     managing
    -0.07
     Payment
    -0.07
     trendy
    -0.07
    イベント
    -0.07
     wichtig
    -0.07
    POSITIVE LOGITS
     nomination
    0.14
     nominations
    0.14
     eligible
    0.13
     nominated
    0.13
     eligibility
    0.12
     nominees
    0.12
     Eligible
    0.12
     nominate
    0.11
     후보
    0.11
     Eligibility
    0.11
    Activations Density 0.033%

    No Known Activations