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. 58471
    Prev
    Next
    INDEX
    Explanations

    wall

    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
     elbow
    -0.08
     insomnia
    -0.08
     loy
    -0.08
     lunes
    -0.07
     ambassador
    -0.07
     forklift
    -0.07
     lunchtime
    -0.07
    iyani
    -0.07
     Inbox
    -0.07
     intensiv
    -0.07
    POSITIVE LOGITS
    rone
    0.08
    護
    0.08
    light
    0.08
     chemically
    0.08
    体系
    0.08
     ornate
    0.08
     coloration
    0.08
    ावट
    0.07
     translucent
    0.07
    reden
    0.07
    Activations Density 0.005%

    No Known Activations