© 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. 30924
    Prev
    Next
    INDEX
    Explanations

    vectors and math notation

    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
     temperature
    -0.09
     cleaning
    -0.09
    _temperature
    -0.08
    _PASS
    -0.08
     (@
    -0.08
    Temperature
    -0.07
    AWS
    -0.07
     temperatures
    -0.07
     Halle
    -0.07
     ratings
    -0.07
    POSITIVE LOGITS
    Vectors
    0.10
     indispens
    0.10
     Basis
    0.10
     độc
    0.10
    豊
    0.09
     redundancy
    0.09
     eindeutig
    0.09
     বিচ
    0.09
     insolv
    0.09
     Neither
    0.09
    Activations Density 0.019%

    No Known Activations