© 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. 44281
    Prev
    Next
    INDEX
    Explanations

    PowerShell scripts

    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
     लड़
    -0.08
     childhood
    -0.08
     wrinkle
    -0.08
     girls
    -0.08
     girl
    -0.07
     लड़की
    -0.07
     London
    -0.07
     epidemi
    -0.07
     chama
    -0.07
     Bluetooth
    -0.07
    POSITIVE LOGITS
    GROUP
    0.08
    jee
    0.08
    _CURSOR
    0.08
    forward
    0.08
     bangs
    0.08
    _GROUP
    0.08
    前
    0.08
    filter
    0.08
    EXEC
    0.08
     seguir
    0.07
    Activations Density 0.005%

    No Known Activations