© 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. 16452
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    -0.10
    েণ
    -0.09
    ொரு
    -0.08
     gezek
    -0.08
    �ლ
    -0.08
    պիս
    -0.08
    �ედ
    -0.08
    �რთიან
    -0.08
    �ხ
    -0.07
    �제
    -0.07
    POSITIVE LOGITS
    ."↵
    0.16
    ."
    0.15
    。我
    0.15
    .".
    0.15
    。
    0.15
    .";
    0.15
    。这
    0.14
    。在
    0.14
    .There
    0.13
    ."↵↵
    0.13
    Activations Density 0.527%
    No Known Activations