© 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. 65344
    Prev
    Next
    INDEX
    Explanations

    Trying not to

    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
     complement
    -0.08
     stamped
    -0.08
    raat
    -0.08
    рых
    -0.07
    ovement
    -0.07
     regard
    -0.07
     annih
    -0.07
     بسته
    -0.07
     بالط
    -0.07
    werkingen
    -0.07
    POSITIVE LOGITS
     upbeat
    0.09
     halluc
    0.09
     laughs
    0.08
     smiles
    0.08
     cheerful
    0.08
     sput
    0.08
     lol
    0.08
     readability
    0.08
     playful
    0.08
     вит
    0.08
    Activations Density 0.019%

    No Known Activations