© 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. 29376
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    —the
    -0.08
     everywhere
    -0.07
     division
    -0.07
    라는
    -0.07
    τυ
    -0.07
    acio
    -0.07
    ે�
    -0.07
    ๆ
    -0.07
    mission
    -0.07
     как
    -0.07
    POSITIVE LOGITS
    িষ্ঠ
    0.08
     తేద
    0.08
     పరి�
    0.08
     Tango
    0.08
     Schedule
    0.08
     Tahun
    0.08
     判
    0.08
     ngủ
    0.08
     Ruta
    0.08
     tetas
    0.07
    Activations Density 0.046%

    No Known Activations