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. 58374
    Prev
    Next
    INDEX
    Explanations

    for

    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
     whenever
    -0.08
     _(
    -0.08
    /licenses
    -0.08
                             ↵
    -0.08
    -License
    -0.08
     lòng
    -0.07
     atendimento
    -0.07
     errno
    -0.07
    /license
    -0.07
    isement
    -0.07
    POSITIVE LOGITS
    の場合
    0.10
     большинства
    0.08
     specifics
    0.08
     modernen
    0.08
    大型
    0.08
    现代
    0.08
    重大
    0.08
     planar
    0.08
     modern
    0.08
     äl
    0.07
    Activations Density 0.078%

    No Known Activations