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. 114035
    Prev
    Next
    INDEX
    Explanations

    atmosphere and light

    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
     buttons
    -0.09
     가치
    -0.08
     deeb
    -0.08
     재미
    -0.08
     책임
    -0.08
    !!!
    -0.08
    价值
    -0.08
    zahlen
    -0.07
     ethereum
    -0.07
     Moch
    -0.07
    POSITIVE LOGITS
     atmospheric
    0.11
     attenuation
    0.11
     Atmospheric
    0.11
     transmitting
    0.10
     interference
    0.10
     airborne
    0.10
     impair
    0.10
    空气
    0.10
     outdoor
    0.10
     terrestre
    0.09
    Activations Density 0.018%

    No Known Activations