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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16713
    Prev
    Next
    INDEX
    Explanations

    relevance crawling

    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
     acompanh
    -0.09
    ADI
    -0.09
     weekends
    -0.08
    Weekend
    -0.08
    兼职
    -0.08
     गया
    -0.08
     acompanhado
    -0.08
     begleitet
    -0.08
     madeira
    -0.08
     aço
    -0.08
    POSITIVE LOGITS
     relevance
    0.12
     craw
    0.12
     interpreting
    0.10
     semantic
    0.10
     콘텐츠
    0.10
     relev
    0.10
     crawling
    0.10
     tokenize
    0.10
     crawl
    0.10
     interpreted
    0.09
    Activations Density 0.014%

    No Known Activations