© 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. 24840
    Prev
    Next
    INDEX
    Explanations

    seeing or looking

    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
     дополнительных
    -0.08
    ühlen
    -0.08
    ubehör
    -0.08
    autions
    -0.08
    _STANDARD
    -0.08
     воздействия
    -0.08
     uten
    -0.08
     основных
    -0.07
    }{↵
    -0.07
    utate
    -0.07
    POSITIVE LOGITS
     puzzled
    0.10
    正在
    0.10
     puzz
    0.10
     confused
    0.09
     perplex
    0.09
     troubling
    0.09
     apparently
    0.09
     wondering
    0.08
     wanting
    0.08
     trying
    0.08
    Activations Density 0.054%

    No Known Activations