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. 19193
    Prev
    Next
    INDEX
    Explanations

    area

    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
    兆
    -0.08
    бычно
    -0.08
     一级
    -0.08
     geta
    -0.08
     сияқты
    -0.08
     Chem
    -0.08
     mnemonic
    -0.07
    주세요
    -0.07
     нь
    -0.07
     suppose
    -0.07
    POSITIVE LOGITS
    difference
    0.12
     difference
    0.12
    Difference
    0.11
    _difference
    0.10
    count
    0.09
    Overlap
    0.09
     Difference
    0.09
     lost
    0.09
     कब्ज
    0.09
     المناطق
    0.09
    Activations Density 0.013%

    No Known Activations