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

    Neuronpedia

    Jacobian LensNEW
    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. 113375
    Prev
    Next
    INDEX
    Explanations

    mathematical solutions

    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
     RAF
    -0.09
     UFC
    -0.09
     FAA
    -0.09
     Russell
    -0.08
     bộ
    -0.08
     rú
    -0.08
     mitochondrial
    -0.08
    uglia
    -0.08
     RFID
    -0.08
    ercul
    -0.08
    POSITIVE LOGITS
     enumerate
    0.09
     Enumer
    0.09
     enumeration
    0.09
     xrange
    0.08
     Ej
    0.08
     Iterate
    0.08
    enumer
    0.08
     enumer
    0.08
     dla
    0.08
     varying
    0.08
    Activations Density 0.045%

    No Known Activations