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. 15-RESID-POST-AA
    6. 28
    Prev
    Next
    INDEX
    Explanations

    LM

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vier
    -0.09
     asparagus
    -0.08
    合法
    -0.08
     Vier
    -0.08
     legal
    -0.08
     lunes
    -0.08
     gült
    -0.08
    Legal
    -0.08
     ailleurs
    -0.08
     celery
    -0.08
    POSITIVE LOGITS
     pretrained
    0.12
     trained
    0.11
    trained
    0.11
    大型
    0.10
    -scale
    0.10
     моделей
    0.09
    模型
    0.09
     embeddings
    0.09
     large
    0.09
    规模
    0.09
    Activations Density 0.081%

    No Known Activations