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. 29865
    Prev
    Next
    INDEX
    Explanations

    memory techniques

    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
     citizenship
    -0.08
     hátt
    -0.08
     healing
    -0.07
     bonding
    -0.07
     Healing
    -0.07
    peaker
    -0.07
     censorship
    -0.07
     demokrat
    -0.07
     swell
    -0.07
     dissolved
    -0.07
    POSITIVE LOGITS
     помещений
    0.08
     помещения
    0.08
     faria
    0.08
    .fake
    0.08
     স্থান
    0.08
     entlang
    0.08
     établissements
    0.08
    栋
    0.08
     Häuser
    0.08
     nyumba
    0.07
    Activations Density 0.001%

    No Known Activations