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. 78711
    Prev
    Next
    INDEX
    Explanations

    GCD calculations

    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
     Reality
    -0.08
    .real
    -0.08
     gerçek
    -0.08
     realities
    -0.08
    יאות
    -0.08
     reality
    -0.08
    _real
    -0.08
     portrayal
    -0.08
    Reality
    -0.07
    omon
    -0.07
    POSITIVE LOGITS
    Subtract
    0.09
     repe
    0.09
    subtract
    0.08
    
    0.08
     subtract
    0.08
    เลือ
    0.08
    狼
    0.08
     остат
    0.08
     subtraction
    0.08
     griev
    0.08
    Activations Density 0.013%

    No Known Activations