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. 131
    Prev
    Next
    INDEX
    Explanations

    ages

    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
    end
    -0.08
    west
    -0.08
    בל
    -0.08
    wari
    -0.07
    endamento
    -0.07
    north
    -0.07
     hefur
    -0.07
    .Resource
    -0.07
    bera
    -0.07
    gle
    -0.07
    POSITIVE LOGITS
     adolescence
    0.12
     adulthood
    0.11
     puberty
    0.11
     usia
    0.11
     sixteen
    0.11
     thirteen
    0.11
     twenties
    0.11
     ηλικ
    0.10
     preco
    0.10
     edad
    0.10
    Activations Density 0.037%

    No Known Activations