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. 111497
    Prev
    Next
    INDEX
    Explanations

    planner

    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
     वैश
    -0.08
    ant
    -0.08
    .zone
    -0.08
     majeure
    -0.07
    _each
    -0.07
    ляд
    -0.07
     beschrieben
    -0.07
     चला
    -0.07
    lat
    -0.07
    chair
    -0.07
    POSITIVE LOGITS
     Hidalgo
    0.09
    (Migration
    0.09
    尼
    0.08
    ocurrency
    0.07
     പറ
    0.07
    -employed
    0.07
    Ка
    0.07
    -energy
    0.07
    СК
    0.07
     méthodes
    0.07
    Activations Density 0.001%

    No Known Activations