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. 30710
    Prev
    Next
    INDEX
    Explanations

    Joshua and promised land

    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
     Raff
    -0.07
     bira
    -0.07
     governors
    -0.07
     Affair
    -0.07
     ترین
    -0.07
    .shutdown
    -0.07
     टिकट
    -0.07
    endidikan
    -0.07
     governor
    -0.07
    pulse
    -0.07
    POSITIVE LOGITS
     iro
    0.09
     jip
    0.09
    ália
    0.08
     territories
    0.08
     criminals
    0.08
    .Asset
    0.07
    �
    0.07
    jum
    0.07
     exuber
    0.07
     Jord
    0.07
    Activations Density 0.005%

    No Known Activations