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. 54016
    Prev
    Next
    INDEX
    Explanations

    salaries and compensation

    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
     donating
    -0.08
     Investing
    -0.08
     investing
    -0.08
     Donate
    -0.08
     tightening
    -0.07
    eteilig
    -0.07
     catastroph
    -0.07
     IService
    -0.07
     investeren
    -0.07
     Close
    -0.07
    POSITIVE LOGITS
    待遇
    0.11
     remuneration
    0.09
    .design
    0.09
     stipend
    0.08
    يه
    0.08
     salaire
    0.08
    250
    0.08
     salaries
    0.08
     designed
    0.08
     salaris
    0.08
    Activations Density 0.038%

    No Known Activations