© 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. 129297
    Prev
    Next
    INDEX
    Explanations

    texting and driving

    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
    .Sum
    -0.08
    Л
    -0.07
    .Sequence
    -0.07
     Пу
    -0.07
     Indonesia
    -0.07
     kwab
    -0.07
    .eb
    -0.07
    hipster
    -0.07
     insects
    -0.07
    ickets
    -0.07
    POSITIVE LOGITS
     dangere
    0.08
     roadway
    0.08
     खत
    0.08
    FDA
    0.08
    עס
    0.08
     dangerous
    0.08
     қара
    0.08
    idamente
    0.08
    -moving
    0.08
    inidad
    0.08
    Activations Density 0.007%

    No Known Activations