Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11865
    Prev
    Next
    INDEX
    Explanations

    Analyzing phrasing/meaning

    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
     ré
    -0.09
    cot
    -0.09
     الط
    -0.08
     \"
    -0.08
     galleries
    -0.08
    tar
    -0.08
     GLES
    -0.08
     જેટ
    -0.08
    [`
    -0.08
     阳
    -0.07
    POSITIVE LOGITS
     nhé
    0.12
    来看
    0.11
    呢
    0.09
    一下
    0.09
     подробнее
    0.08
     देखें
    0.08
    Anyway
    0.08
    Actually
    0.08
    吧
    0.08
     mechanically
    0.08
    Activations Density 0.131%

    No Known Activations