© 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. 488
    Prev
    Next
    INDEX
    Explanations

    code snippets/formulas

    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
    Compressed
    -0.08
     assessed
    -0.08
    书记
    -0.07
    压
    -0.07
    Electronic
    -0.07
    Submitting
    -0.07
     комиссия
    -0.07
    推
    -0.07
    Jazz
    -0.07
    Dress
    -0.07
    POSITIVE LOGITS
    Occurrences
    0.12
     occurrences
    0.12
    次数
    0.09
     lần
    0.09
     repetitions
    0.09
    一次
    0.08
    _Remove
    0.08
     miejsc
    0.08
     Replace
    0.08
     nummer
    0.08
    Activations Density 0.007%

    No Known Activations