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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112138
    Prev
    Next
    INDEX
    Explanations

    oil

    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
     seats
    -0.09
    �
    -0.09
     Seats
    -0.09
     Value
    -0.08
    Seats
    -0.08
     genocide
    -0.08
    value
    -0.08
     Sofa
    -0.08
     Seat
    -0.07
     conversational
    -0.07
    POSITIVE LOGITS
     보호
    0.09
     protection
    0.09
    <Texture
    0.09
     protective
    0.09
    监察
    0.09
    保护
    0.09
    িং
    0.08
     protecting
    0.08
     proteg
    0.08
     bescherming
    0.08
    Activations Density 0.004%

    No Known Activations