© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5838
    Prev
    Next
    INDEX
    Explanations

    A

    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
    Isso
    -0.12
    Edges
    -0.12
    Elements
    -0.11
    Employees
    -0.11
    Options
    -0.11
    Episodes
    -0.11
    Achievements
    -0.11
    Events
    -0.11
    Entities
    -0.11
    Essa
    -0.11
    POSITIVE LOGITS
     Different
    0.16
     Better
    0.16
     Thousand
    0.16
     Few
    0.15
     Simple
    0.14
     Million
    0.14
     Small
    0.14
     New
    0.14
     Strange
    0.14
     Very
    0.13
    Activations Density 0.017%

    No Known Activations