© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103538
    Prev
    Next
    INDEX
    Explanations

    Initial

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第一
    -0.12
    	first
    -0.11
     first
    -0.11
    first
    -0.10
    (first
    -0.10
     primeira
    -0.10
     pierws
    -0.10
     glav
    -0.10
     main
    -0.09
    .first
    -0.09
    POSITIVE LOGITS
     Initially
    0.33
     initial
    0.33
     initially
    0.32
    Initially
    0.32
    initial
    0.31
     inicialmente
    0.30
    Initial
    0.30
    (initial
    0.29
     Initial
    0.29
    _initial
    0.29
    Activations Density 0.107%

    No Known Activations