© 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. 99518
    Prev
    Next
    INDEX
    Explanations

    +

    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
    ізації
    -0.09
     Singles
    -0.08
    Ё
    -0.08
    стэр
    -0.08
     Zudem
    -0.08
     sluts
    -0.08
     сов
    -0.08
     fraaie
    -0.08
    isis
    -0.08
    -module
    -0.08
    POSITIVE LOGITS
     juntos
    0.08
    	gpio
    0.08
    Together
    0.08
     beacon
    0.08
     skupaj
    0.08
     Capitol
    0.08
    ARC
    0.08
     (+
    0.08
     together
    0.08
     adhere
    0.08
    Activations Density 0.005%

    No Known Activations