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. 30575
    Prev
    Next
    INDEX
    Explanations

    Application

    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
     countertops
    -0.08
     drill
    -0.08
     drilling
    -0.08
     entail
    -0.08
     demolition
    -0.08
    awai
    -0.08
     laminate
    -0.07
     PEC
    -0.07
     delete
    -0.07
    ction
    -0.07
    POSITIVE LOGITS
     公司
    0.09
    Ints
    0.09
     Injectable
    0.08
     bless
    0.08
    Extended
    0.08
     Intelig
    0.08
     根
    0.08
     初始化
    0.08
    .NODE
    0.08
    (QObject
    0.08
    Activations Density 0.001%

    No Known Activations