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. 15-RESID-POST-AA
    6. 19526
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Former
    -0.09
     אם
    -0.08
    _bool
    -0.08
    _fake
    -0.08
     উন্ন
    -0.07
    _match
    -0.07
     {"
    -0.07
    	match
    -0.07
    Elite
    -0.07
    _demo
    -0.07
    POSITIVE LOGITS
     positively
    0.10
     noon
    0.09
    -axis
    0.09
     longitude
    0.09
     clockwise
    0.09
     positivo
    0.09
     eixo
    0.09
     positif
    0.09
     dólar
    0.09
     GMT
    0.08
    Activations Density 0.002%

    No Known Activations