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. 98189
    Prev
    Next
    INDEX
    Explanations

    Work

    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
     clé
    -0.08
    法
    -0.08
     edə
    -0.08
    visi
    -0.08
    ellinen
    -0.08
    τή
    -0.08
     Upt
    -0.07
     Boston
    -0.07
    법
    -0.07
    éfono
    -0.07
    POSITIVE LOGITS
    薪
    0.12
    会
    0.10
    伤
    0.10
    人工
    0.09
    商业
    0.09
    資
    0.09
    资产
    0.09
    會
    0.08
     会
    0.08
    作者
    0.08
    Activations Density 0.001%

    No Known Activations