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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120141
    Prev
    Next
    INDEX
    Explanations

    machine, device

    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
     terci
    -0.08
     cà
    -0.08
     dí
    -0.08
     populous
    -0.08
     erupted
    -0.08
     excl
    -0.08
     Michigan
    -0.08
     ilgili
    -0.07
     영역
    -0.07
     cv
    -0.07
    POSITIVE LOGITS
     malfunction
    0.13
    devices
    0.12
     Devices
    0.11
    设备
    0.11
     portátil
    0.11
     devices
    0.11
     inventions
    0.11
     устройства
    0.10
     apparatus
    0.10
     apparaat
    0.10
    Activations Density 0.052%

    No Known Activations