© 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. 112474
    Prev
    Next
    INDEX
    Explanations

    solution calculations

    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
     awards
    -0.08
     Coin
    -0.07
     Award
    -0.07
     reflecting
    -0.07
     "*
    -0.07
     $("#
    -0.07
     "*"
    -0.07
     */}↵
    -0.07
    ร
    -0.07
     beyond
    -0.07
    POSITIVE LOGITS
     Desired
    0.16
    Desired
    0.15
    desired
    0.15
     desired
    0.14
     gewenste
    0.12
     gewünsch
    0.12
     원하는
    0.11
     desej
    0.11
     gewünschten
    0.11
    Wanted
    0.11
    Activations Density 0.012%

    No Known Activations