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. 130353
    Prev
    Next
    INDEX
    Explanations

    sensors

    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
     witty
    -0.10
     postul
    -0.10
     literal
    -0.09
     verbal
    -0.09
     संकट
    -0.08
    Literal
    -0.08
     spontane
    -0.08
     Literal
    -0.08
    制度
    -0.08
     celebrations
    -0.08
    POSITIVE LOGITS
    型号
    0.14
     USB
    0.14
    规格
    0.14
    厂家
    0.13
     manufacturers
    0.13
     manufacturer
    0.12
     Sony
    0.12
     OEM
    0.12
     FPGA
    0.12
     Qualcomm
    0.12
    Activations Density 0.003%

    No Known Activations