© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79262
    Prev
    Next
    INDEX
    Explanations

    testing failure conditions

    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
     сотруднич
    -0.08
     usable
    -0.08
     agréable
    -0.08
    _c
    -0.07
     किसानों
    -0.07
     אנשים
    -0.07
    thanks
    -0.07
     contributed
    -0.07
    jir
    -0.07
    产业
    -0.07
    POSITIVE LOGITS
     intentionally
    0.15
     deliberately
    0.14
     purposely
    0.14
     artificially
    0.13
    模拟
    0.13
     simulated
    0.12
    simulate
    0.12
     scenarios
    0.12
     deliberate
    0.11
     intentional
    0.11
    Activations Density 0.027%

    No Known Activations