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. 43329
    Prev
    Next
    INDEX
    Explanations

    family

    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
    ंच
    -0.08
    ынам
    -0.08
     naar
    -0.08
     knocks
    -0.08
    Vars
    -0.07
     nál
    -0.07
     красив
    -0.07
     atrav
    -0.07
     anemia
    -0.07
    øte
    -0.07
    POSITIVE LOGITS
     mentorship
    0.09
     içinde
    0.09
     Philosoph
    0.08
    .webp
    0.08
    folk
    0.08
     philosopher
    0.08
     Familia
    0.08
    伦理
    0.08
     household
    0.08
     Tala
    0.08
    Activations Density 0.025%

    No Known Activations