© 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. 54327
    Prev
    Next
    INDEX
    Explanations

    rear

    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
     ba
    -0.08
     Had
    -0.08
    /key
    -0.08
     wan
    -0.08
     Waik
    -0.08
    /be
    -0.07
     동안
    -0.07
     ​​
    -0.07
    _prior
    -0.07
     ka
    -0.07
    POSITIVE LOGITS
    ுடைய
    0.09
    δυ
    0.08
     homen
    0.08
     pinnacle
    0.08
    ieving
    0.08
     ratt
    0.07
    ಳಿ
    0.07
    dita
    0.07
     Ron
    0.07
    aven
    0.07
    Activations Density 0.005%

    No Known Activations