© 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. 11-RESID-POST-AA
    11. 29690
    Prev
    Next
    INDEX
    Explanations

    Code, serialization

    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
     föret
    -0.09
     적극
    -0.08
     váll
    -0.08
    COVID
    -0.08
     bullish
    -0.08
     COVID
    -0.08
     covid
    -0.08
     skincare
    -0.07
    Abs
    -0.07
     Covid
    -0.07
    POSITIVE LOGITS
    Serializable
    0.14
    pickle
    0.13
     сериал
    0.13
     Serializable
    0.13
    serialized
    0.13
    .serialize
    0.13
     serialize
    0.12
    serialization
    0.12
     serialized
    0.12
    serialize
    0.12
    Activations Density 0.006%

    No Known Activations