© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97244
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .fn
    -0.09
     bezpieczeń
    -0.09
     ufa
    -0.09
     felis
    -0.09
     toont
    -0.09
    decoder
    -0.09
    _serializer
    -0.08
     Codable
    -0.08
     Entscheidungen
    -0.08
    serde
    -0.08
    POSITIVE LOGITS
     tang
    0.14
     intersection
    0.12
     concurrency
    0.12
     concurrence
    0.11
     incidence
    0.11
    intersection
    0.11
     coincidence
    0.10
    Concurrency
    0.10
     application
    0.10
     intersections
    0.10
    Activations Density 0.004%

    No Known Activations