© 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. 23-RESID-POST-AA
    11. 49033
    Prev
    Next
    INDEX
    Explanations

    marching

    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
    训练
    -0.09
     trainingen
    -0.09
     প্রশ
    -0.09
    dives
    -0.08
     Training
    -0.08
    plements
    -0.08
     overnight
    -0.08
     Overnight
    -0.08
     प्रशिक्षण
    -0.08
     noches
    -0.08
    POSITIVE LOGITS
     marching
    0.13
     मार्च
    0.13
     march
    0.13
     March
    0.12
     brisk
    0.12
     jogging
    0.11
     cardiovascular
    0.11
    March
    0.11
     марш
    0.11
     মার্চ
    0.11
    Activations Density 0.016%

    No Known Activations