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. 44213
    Prev
    Next
    INDEX
    Explanations

    DFS

    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
     tiers
    -0.10
     лиценз
    -0.09
     upgrade
    -0.09
     lic
    -0.08
     бю
    -0.08
    tiers
    -0.08
     Patent
    -0.08
     bills
    -0.08
     изготов
    -0.08
     ingenious
    -0.08
    POSITIVE LOGITS
     traversal
    0.15
    Traversal
    0.13
    遍
    0.13
     Travers
    0.12
     visiting
    0.12
     visitation
    0.12
     travers
    0.11
     DFS
    0.11
    Traverse
    0.11
     exploring
    0.10
    Activations Density 0.005%

    No Known Activations