© 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. 11-RESID-POST-AA
    11. 64880
    Prev
    Next
    INDEX
    Explanations

    ffmpeg image sequences

    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
     domicile
    -0.09
    Domestic
    -0.09
    itaal
    -0.09
    Upgradeable
    -0.08
     forest
    -0.08
     domestic
    -0.08
    uggish
    -0.08
     Domestic
    -0.08
     Firm
    -0.08
    ్యత
    -0.08
    POSITIVE LOGITS
     numbering
    0.13
     nummer
    0.10
    番号
    0.09
    号
    0.09
    编号
    0.09
     interpol
    0.09
     numbered
    0.08
     indexing
    0.08
    循环
    0.08
    电影
    0.08
    Activations Density 0.004%

    No Known Activations