© 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. 19-RESID-POST-AA
    11. 103511
    Prev
    Next
    INDEX
    Explanations

    positive achievements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we're
    -0.08
    ’ou
    -0.08
     പോയ
    -0.08
     diligently
    -0.08
     accurately
    -0.08
     faithfully
    -0.08
     shortly
    -0.08
     bijdrage
    -0.08
     Award
    -0.08
     Kategorien
    -0.07
    POSITIVE LOGITS
    决定
    0.10
     desirable
    0.10
     encouraging
    0.09
     desired
    0.09
     اچھ
    0.08
     remarkable
    0.08
     원하는
    0.08
     virt
    0.08
     حکومت
    0.08
    疫情
    0.08
    Activations Density 0.001%

    No Known Activations