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. 114027
    Prev
    Next
    INDEX
    Explanations

    Chinese and English, people

    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
    clinic
    -0.07
    ವಾದ
    -0.07
    angal
    -0.07
     ?)
    -0.07
     Gustavo
    -0.07
     dheer
    -0.07
     dalawang
    -0.07
    మైన
    -0.07
     ep
    -0.07
    abby
    -0.07
    POSITIVE LOGITS
     collectively
    0.15
     সবাই
    0.12
    _except
    0.11
     allemaal
    0.11
     collective
    0.10
     omkring
    0.10
     모두
    0.10
     Collective
    0.10
     unanimous
    0.10
    versammlung
    0.10
    Activations Density 0.285%

    No Known Activations