© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43574
    Prev
    Next
    INDEX
    Explanations

    Grand Slam tennis

    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
    cells
    -0.08
     número
    -0.08
    ीस
    -0.08
    Int
    -0.08
    ingss
    -0.08
     نه
    -0.08
     loud
    -0.08
    _int
    -0.08
     Int
    -0.08
     خوش
    -0.08
    POSITIVE LOGITS
     혁
    0.09
     contrib
    0.09
     botanical
    0.08
     boutique
    0.08
     textile
    0.08
     perkembangan
    0.08
     Berger
    0.08
     organizational
    0.07
     gz
    0.07
     manifesta
    0.07
    Activations Density 0.002%

    No Known Activations