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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44827
    Prev
    Next
    INDEX
    Explanations

    MJ

    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
     Mecklenburg
    -0.08
    ालाई
    -0.08
     :(↵↵
    -0.08
    ుకున్న
    -0.08
    Interestingly
    -0.08
     Εκ
    -0.08
    Fib
    -0.07
    وتر
    -0.07
    fro
    -0.07
     fro
    -0.07
    POSITIVE LOGITS
    がお
    0.09
    帮助
    0.08
    优势
    0.08
     sunsets
    0.08
     interdisciplinary
    0.08
     преимущества
    0.08
     unparalleled
    0.08
     提
    0.08
     मदद
    0.08
     nej
    0.07
    Activations Density 0.058%

    No Known Activations