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

    Neuronpedia

    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. 7498
    Prev
    Next
    INDEX
    Explanations

    II

    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
     Am
    -0.07
     месяц
    -0.07
     rate
    -0.07
     spring
    -0.07
     sprung
    -0.07
     DEV
    -0.07
     entr
    -0.07
     haar
    -0.07
     gesproken
    -0.07
     hablan
    -0.07
    POSITIVE LOGITS
     mystical
    0.08
    oksia
    0.08
    Execut
    0.08
    ุป
    0.08
    licable
    0.08
    ํ
    0.07
     ezek
    0.07
    ્
    0.07
    gli
    0.07
     outing
    0.07
    Activations Density 0.001%

    No Known Activations