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. 98545
    Prev
    Next
    INDEX
    Explanations

    、

    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
    その
    -0.30
    それ
    -0.30
    「
    -0.29
    この
    -0.29
    日本
    -0.25
    お
    -0.24
    新
    -0.23
    市場
    -0.23
    お気
    -0.23
    『
    -0.23
    POSITIVE LOGITS
    以及
    0.12
     illetve
    0.12
    そして
    0.12
     чтобы
    0.11
     albeit
    0.10
     valamint
    0.10
     etc
    0.10
     щоб
    0.10
     однако
    0.10
     což
    0.09
    Activations Density 0.044%

    No Known Activations