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. 111559
    Prev
    Next
    INDEX
    Explanations

    it

    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
     نظ
    -0.09
     Km
    -0.08
     Pins
    -0.08
    'analyse
    -0.08
    '''
    -0.08
     convertido
    -0.07
    ೋಗ
    -0.07
    -0.07
     Aman
    -0.07
    ş
    -0.07
    POSITIVE LOGITS
     abdomen
    0.08
     nopeasti
    0.08
     swiftly
    0.08
     figur
    0.08
    腹
    0.08
     tiyan
    0.08
     abdominal
    0.08
    迅
    0.08
     живот
    0.08
     Veterans
    0.08
    Activations Density 0.003%

    No Known Activations