© 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 EvalsExportsinterp-engineNEWAPI 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. 110639
    Prev
    Next
    INDEX
    Explanations

    error

    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
    🏻
    -0.08
     Ban
    -0.08
     governor
    -0.07
    🏼
    -0.07
    minus
    -0.07
    -sama
    -0.07
     Elaine
    -0.07
     Bahamas
    -0.07
     Wil
    -0.07
    EMS
    -0.07
    POSITIVE LOGITS
    -benar
    0.09
    Occurred
    0.08
     succ
    0.08
    hafte
    0.08
    Vent
    0.08
    lessness
    0.07
    bun
    0.07
    acies
    0.07
    ADM
    0.07
     Buchanan
    0.07
    Activations Density 0.020%

    No Known Activations