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. 65797
    Prev
    Next
    INDEX
    Explanations

    mathematical inverses and operations

    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
     profondeur
    -0.08
     allure
    -0.08
    _py
    -0.08
    移动
    -0.08
     móviles
    -0.08
     excurs
    -0.07
     verandering
    -0.07
     स्थल
    -0.07
    석
    -0.07
     voyeur
    -0.07
    POSITIVE LOGITS
     birlikte
    0.08
     علیه
    0.08
    财神
    0.08
     തമ്മ
    0.08
    untur
    0.08
    .one
    0.08
    ả
    0.08
    egn
    0.07
    zum
    0.07
     свя
    0.07
    Activations Density 0.016%

    No Known Activations