© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102872
    Prev
    Next
    INDEX
    Explanations

    Chemical notations

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     explosions
    -0.09
    Extraction
    -0.09
     extracting
    -0.09
     extraction
    -0.09
     stripping
    -0.08
     uprising
    -0.08
     Extraction
    -0.08
     destruction
    -0.08
     emanc
    -0.08
     leaks
    -0.08
    POSITIVE LOGITS
    erged
    0.11
     возб
    0.11
     produto
    0.11
    _Product
    0.10
     Produto
    0.10
     продукт
    0.10
    	product
    0.10
    וצר
    0.10
     intermedi
    0.10
    <Product
    0.10
    Activations Density 0.003%

    No Known Activations