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. 120434
    Prev
    Next
    INDEX
    Explanations

    immigration

    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
     says
    -0.08
    anggap
    -0.08
     قول
    -0.08
    amiliar
    -0.08
    without
    -0.07
    ানা
    -0.07
    ív
    -0.07
     without
    -0.07
     layout
    -0.07
     lune
    -0.07
    POSITIVE LOGITS
     fleeing
    0.13
     emigr
    0.11
     refugees
    0.11
     persecution
    0.10
     эми
    0.10
    Migration
    0.10
    迁
    0.10
     migrants
    0.10
     migrating
    0.10
     Migration
    0.10
    Activations Density 0.033%

    No Known Activations