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. 43625
    Prev
    Next
    INDEX
    Explanations

    主题

    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
    RG
    -0.08
     hay
    -0.07
    .cell
    -0.07
     Mapping
    -0.07
     conn
    -0.07
     odi
    -0.07
    iar
    -0.07
     gior
    -0.07
     газет
    -0.07
     لی
    -0.07
    POSITIVE LOGITS
    sef
    0.07
    חדש
    0.07
    स्थ
    0.07
    ः
    0.07
    dress
    0.07
     promptly
    0.07
    हर
    0.07
     wan
    0.07
    Innovation
    0.07
     trough
    0.07
    Activations Density 0.005%

    No Known Activations