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. 9068
    Prev
    Next
    INDEX
    Explanations

    vector search algorithms

    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
     univer
    -0.09
     prostřed
    -0.08
     uninstall
    -0.07
     GOV
    -0.07
    遵
    -0.07
    自慰
    -0.07
    用品
    -0.07
     SUBSTITUTE
    -0.07
    改革
    -0.07
     universal
    -0.07
    POSITIVE LOGITS
     querying
    0.12
     查询
    0.12
    Nearest
    0.11
     queried
    0.11
    查询
    0.10
    nearest
    0.10
    Query
    0.10
    -query
    0.10
    query
    0.09
     nearest
    0.09
    Activations Density 0.005%

    No Known Activations