© 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. 96274
    Prev
    Next
    INDEX
    Explanations

    777

    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
     cola
    -0.09
     COL
    -0.08
    cola
    -0.08
     mah
    -0.08
     converse
    -0.08
     Cola
    -0.08
     Mr
    -0.08
    olab
    -0.08
    laş
    -0.08
     Fern
    -0.07
    POSITIVE LOGITS
    777
    0.10
    (te
    0.08
    638
    0.08
    (session
    0.08
     көз
    0.08
    (turn
    0.08
    78
    0.08
    (page
    0.08
    (pointer
    0.08
    geen
    0.08
    Activations Density 0.002%

    No Known Activations