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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130816
    Prev
    Next
    INDEX
    Explanations

    公

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bear
    -0.08
     lai
    -0.08
    Bear
    -0.08
    ual
    -0.07
    uation
    -0.07
     bearer
    -0.07
     bearbeiten
    -0.07
     bear
    -0.07
     terminal
    -0.07
    .authorization
    -0.07
    POSITIVE LOGITS
    relations
    0.15
     Relations
    0.14
     relations
    0.14
    关
    0.12
    Relations
    0.12
    关系
    0.11
    關
    0.11
    関
    0.11
    rels
    0.11
     relaciones
    0.10
    Activations Density 0.001%

    No Known Activations