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. 43911
    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
     Newton
    -0.08
    bones
    -0.08
    有限公司
    -0.08
    /widget
    -0.08
     drawable
    -0.08
     Banco
    -0.08
     Electronics
    -0.08
    .hardware
    -0.08
    ardware
    -0.08
     operands
    -0.08
    POSITIVE LOGITS
     refugee
    0.18
     refugees
    0.18
     deport
    0.15
     immigration
    0.15
     humanitarian
    0.15
     asylum
    0.14
     migrants
    0.14
     Refuge
    0.14
     homeless
    0.13
     inmigr
    0.13
    Activations Density 0.058%

    No Known Activations