© 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. 110506
    Prev
    Next
    INDEX
    Explanations

    Ingredients names

    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
    Dis
    -0.08
    .So
    -0.08
     наф
    -0.08
    وقات
    -0.08
    -Ray
    -0.07
    .DIS
    -0.07
    (verbose
    -0.07
    thermal
    -0.07
     Rockies
    -0.07
    П
    -0.07
    POSITIVE LOGITS
     HAL
    0.08
     predecessors
    0.08
    rim
    0.07
     lancé
    0.07
     secrecy
    0.07
    sealed
    0.07
     LORD
    0.07
     произ
    0.07
     pineapple
    0.07
     immort
    0.07
    Activations Density 0.003%

    No Known Activations