Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2480
    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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sicher
    -0.07
     olds
    -0.07
     thức
    -0.07
    -Ste
    -0.07
     doble
    -0.07
     fidel
    -0.07
     entrant
    -0.07
     refin
    -0.07
    ,我
    -0.07
     ding
    -0.07
    POSITIVE LOGITS
     Elliott
    0.08
    .bound
    0.08
     Fred
    0.08
    ente
    0.08
     карти
    0.07
    .websocket
    0.07
     xpath
    0.07
     каза
    0.07
    qr
    0.07
     Skate
    0.07
    Activations Density 0.001%

    No Known Activations