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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 53115
    Prev
    Next
    INDEX
    Explanations

    runner

    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
     son's
    -0.08
    campo
    -0.08
     vende
    -0.08
     daughter's
    -0.08
    74
    -0.08
    mé
    -0.07
     divides
    -0.07
     incendi
    -0.07
    ucleus
    -0.07
     Transparency
    -0.07
    POSITIVE LOGITS
    凝
    0.08
     debat
    0.08
     түрде
    0.08
    Ợ
    0.08
     কর
    0.08
    ,,
    0.07
    uest
    0.07
    (coeff
    0.07
    ில்
    0.07
    .bn
    0.07
    Activations Density 0.001%

    No Known Activations