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. 77192
    Prev
    Next
    INDEX
    Explanations

    the

    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
     complements
    -0.08
    fonts
    -0.08
    Мак
    -0.07
     fallen
    -0.07
    /,
    -0.07
     emitted
    -0.07
    Ν
    -0.07
     fall
    -0.07
     falling
    -0.07
     pies
    -0.07
    POSITIVE LOGITS
    VIII
    0.08
    นะ
    0.08
     refrigeration
    0.08
    ندگی
    0.08
     gym
    0.07
    ുണ്ട്
    0.07
     thermostat
    0.07
    保存
    0.07
     այնտեղ
    0.07
    _shared
    0.07
    Activations Density 0.020%

    No Known Activations