Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45063
    Prev
    Next
    INDEX
    Explanations

    the number 4

    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
     nes
    -0.08
    widget
    -0.08
     radioactive
    -0.07
     UHD
    -0.07
     proton
    -0.07
     CD
    -0.07
    proxy
    -0.07
    1
    -0.07
    <context
    -0.07
     RFID
    -0.07
    POSITIVE LOGITS
     industriya
    0.09
     đất
    0.08
     గ
    0.08
     INDUSTR
    0.08
     Industria
    0.08
     Industry
    0.08
     già
    0.07
     જેવા
    0.07
     butikker
    0.07
     атмос
    0.07
    Activations Density 0.001%

    No Known Activations