© 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. 91665
    Prev
    Next
    INDEX
    Explanations

    apostrophe

    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
     legends
    -0.07
    	RTLU
    -0.07
     appears
    -0.07
     totaled
    -0.07
    ‬↵↵
    -0.07
     skal
    -0.07
    �
    -0.07
    ?.↵↵
    -0.07
     scams
    -0.07
     제목
    -0.07
    POSITIVE LOGITS
    Buscar
    0.08
    oplas
    0.07
     control
    0.07
    Cari
    0.07
     integrity
    0.07
     comporte
    0.07
     originally
    0.07
     resign
    0.07
    ться
    0.07
     gerçekten
    0.07
    Activations Density 0.012%

    No Known Activations