© 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. 65325
    Prev
    Next
    INDEX
    Explanations

    synonyms

    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
    锅
    -0.08
    392
    -0.08
     Protestant
    -0.07
    gid
    -0.07
    正确
    -0.07
     Gladi
    -0.07
    ଧ
    -0.07
    onite
    -0.07
     Malware
    -0.07
    恶
    -0.07
    POSITIVE LOGITS
     everytime
    0.10
     tránh
    0.09
    Avoid
    0.09
     variability
    0.09
     evitando
    0.09
     synonyms
    0.09
    variation
    0.09
     evitare
    0.08
     избег
    0.08
     decât
    0.08
    Activations Density 0.017%

    No Known Activations