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. 23-RESID-POST-AA
    6. 98679
    Prev
    Next
    INDEX
    Explanations

    -d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    889
    -0.08
     akun
    -0.08
     gider
    -0.08
    онки
    -0.08
     QU
    -0.08
     Bulldogs
    -0.08
     milliseconds
    -0.07
    109
    -0.07
     kuuk
    -0.07
     james
    -0.07
    POSITIVE LOGITS
    ye
    0.07
    Concern
    0.07
    Progress
    0.07
     specialise
    0.07
     grunn
    0.07
     전문
    0.07
    šanu
    0.07
    izes
    0.07
    adal
    0.07
    .Progress
    0.07
    Activations Density 0.002%

    No Known Activations