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. 78721
    Prev
    Next
    INDEX
    Explanations

    Hips/Pelvis

    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
     MPs
    -0.08
     harassment
    -0.08
     predictions
    -0.08
     переговор
    -0.08
    _predict
    -0.08
    หาร
    -0.08
    견
    -0.08
     negotiation
    -0.07
    资格
    -0.07
    Students
    -0.07
    POSITIVE LOGITS
    关闭
    0.08
     अद
    0.08
     níveis
    0.08
     frente
    0.07
    h
    0.07
    水平
    0.07
     Amid
    0.07
    _rotation
    0.07
    位置
    0.07
    .example
    0.07
    Activations Density 0.004%

    No Known Activations