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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 55554
    Prev
    Next
    INDEX
    Explanations

    coaching

    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
    vao
    -0.10
     varchar
    -0.08
    varchar
    -0.08
    655
    -0.08
    ক্ষ
    -0.08
    ادن
    -0.08
    字符
    -0.08
    curl
    -0.08
    vell
    -0.08
     randint
    -0.08
    POSITIVE LOGITS
     coaching
    0.15
     Coaching
    0.15
     coach
    0.13
     Coach
    0.12
     begeleiding
    0.11
    coach
    0.11
    Coach
    0.11
     консульта
    0.11
     상담
    0.11
     mentoring
    0.11
    Activations Density 0.061%

    No Known Activations