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. 43674
    Prev
    Next
    INDEX
    Explanations

    ±

    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
     announcement
    -0.08
    ု
    -0.08
    emotion
    -0.08
     Reich
    -0.08
    ကို
    -0.08
    နှ
    -0.08
     agreement
    -0.08
    တဲ့
    -0.08
    announcement
    -0.08
     filmer
    -0.07
    POSITIVE LOGITS
     методы
    0.09
     варианты
    0.09
    warz
    0.08
    xbe
    0.08
    umbi
    0.08
     способы
    0.07
     Donate
    0.07
    BB
    0.07
    yard
    0.07
    wc
    0.07
    Activations Density 0.004%

    No Known Activations