© 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. 11-RESID-POST-AA
    11. 79398
    Prev
    Next
    INDEX
    Explanations

    Maven

    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
     vah
    -0.08
    /off
    -0.07
     Isla
    -0.07
    ipa
    -0.07
     rédu
    -0.07
    perform
    -0.07
    각
    -0.07
    割
    -0.07
     relativement
    -0.07
     alleged
    -0.07
    POSITIVE LOGITS
     clay
    0.09
     rosas
    0.08
     Mellon
    0.08
     overdue
    0.08
     Magnum
    0.08
    clientes
    0.07
     fined
    0.07
     Milling
    0.07
     filos
    0.07
     Heel
    0.07
    Activations Density 0.001%

    No Known Activations