© 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. 99633
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     innovations
    -0.09
     Nay
    -0.08
    derdag
    -0.08
     Př
    -0.08
     tackles
    -0.08
    Ted
    -0.07
     Innovations
    -0.07
     saker
    -0.07
     مطالب
    -0.07
     നവ
    -0.07
    POSITIVE LOGITS
     अर्थात
    0.09
     એટલે
    0.08
     entiendo
    0.08
    ??
    0.08
     establecimiento
    0.08
    ???
    0.08
    ??↵
    0.08
     అంటే
    0.08
    ??↵↵
    0.08
    φορ
    0.08
    Activations Density 0.054%

    No Known Activations