© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31306
    Prev
    Next
    INDEX
    Explanations

    punctuation, common words

    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
    aderno
    -0.08
     C
    -0.08
     zil
    -0.07
    排行
    -0.07
     foundational
    -0.07
     Lyrics
    -0.07
     Debt
    -0.07
     Wochen
    -0.07
     weekly
    -0.07
     զ
    -0.07
    POSITIVE LOGITS
    .savefig
    0.13
     TIFF
    0.10
    Save
    0.10
    /save
    0.09
    .save
    0.09
    -save
    0.09
    .Save
    0.09
    (save
    0.08
    Keyword
    0.08
    _Save
    0.08
    Activations Density 0.005%

    No Known Activations