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. 53995
    Prev
    Next
    INDEX
    Explanations

    legal principles

    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
     scientifically
    -0.08
    afet
    -0.08
    encie
    -0.08
     callback
    -0.07
    ếp
    -0.07
     Wikimedia
    -0.07
     Mozilla
    -0.07
     night
    -0.07
     region
    -0.07
    Culture
    -0.07
    POSITIVE LOGITS
     unjust
    0.11
     обстоятель
    0.09
     undesirable
    0.09
     আদাল
    0.09
     Pry
    0.08
     sovereign
    0.08
     अदालत
    0.08
     കോടത
    0.08
     daños
    0.08
     doctrines
    0.08
    Activations Density 0.031%

    No Known Activations