© 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. 108385
    Prev
    Next
    INDEX
    Explanations

    ly

    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
     charity
    -0.09
     нужна
    -0.08
     Pharmacy
    -0.08
    찍
    -0.08
     सारी
    -0.07
    еры
    -0.07
    ера
    -0.07
     Qo
    -0.07
     регуляр
    -0.07
     profits
    -0.07
    POSITIVE LOGITS
     Narrative
    0.08
     Dose
    0.08
    LOS
    0.08
     Los
    0.08
     Donovan
    0.07
     wilt
    0.07
     Bonn
    0.07
    ैन
    0.07
    .sh
    0.07
     Donner
    0.07
    Activations Density 0.001%

    No Known Activations