© 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. 3-RESID-POST-AA
    11. 12893
    Prev
    Next
    INDEX
    Explanations

    complacent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    이크
    -0.08
     suele
    -0.08
     Très
    -0.07
     gráfica
    -0.07
     Tru
    -0.07
     Konz
    -0.07
     Inject
    -0.07
    tru
    -0.07
     동일
    -0.07
    inject
    -0.07
    POSITIVE LOGITS
     march
    0.08
    Yang
    0.07
     requ
    0.07
     ਮ
    0.07
    ’h
    0.07
     fitted
    0.07
     cunning
    0.07
    .Security
    0.07
    'h
    0.07
    Initialized
    0.07
    Activations Density 0.002%

    No Known Activations