© 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. 26271
    Prev
    Next
    INDEX
    Explanations

    firm

    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
    అ
    -0.08
     Garland
    -0.07
    WG
    -0.07
     inequality
    -0.07
     myocardial
    -0.07
     flim
    -0.07
     Webseiten
    -0.07
     fus
    -0.07
     node
    -0.07
     कल्प
    -0.07
    POSITIVE LOGITS
    টির
    0.10
     Bast
    0.08
     бары
    0.08
     Bahrain
    0.08
    টি
    0.08
     Baldwin
    0.07
     tersebut
    0.07
     ursprünglich
    0.07
    -là
    0.07
     Barca
    0.07
    Activations Density 0.392%

    No Known Activations