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. 43213
    Prev
    Next
    INDEX
    Explanations

    software and the coup

    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
     oferecem
    -0.08
     geop
    -0.08
     aanbiedingen
    -0.08
     Updates
    -0.07
     gostam
    -0.07
     soluble
    -0.07
     seaside
    -0.07
     oferece
    -0.07
     traders
    -0.07
     Ocean
    -0.07
    POSITIVE LOGITS
    あ
    0.10
    ДА
    0.09
     wells
    0.09
    Regardless
    0.08
    _sn
    0.08
     دع
    0.07
    対象
    0.07
    да
    0.07
     مبار
    0.07
     läh
    0.07
    Activations Density 0.000%

    No Known Activations