© 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. 23-RESID-POST-AA
    11. 97445
    Prev
    Next
    INDEX
    Explanations

    math functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (Array
    -0.11
    [String
    -0.10
    =["
    -0.10
    (['
    -0.10
     ['
    -0.10
    [Double
    -0.10
     Array
    -0.09
    =['
    -0.09
    [np
    -0.09
    	Array
    -0.09
    POSITIVE LOGITS
     abs
    0.18
    (abs
    0.17
    abs
    0.15
    (pow
    0.15
     float
    0.14
     round
    0.14
     pow
    0.13
    (float
    0.12
    (round
    0.12
     int
    0.12
    Activations Density 0.016%

    No Known Activations