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. 117641
    Prev
    Next
    INDEX
    Explanations

    ly

    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
     hopeful
    -0.08
    yield
    -0.08
     thành
    -0.08
    °
    -0.08
     takeover
    -0.08
     अउ
    -0.08
    ಿಲ
    -0.07
     위한
    -0.07
    ayout
    -0.07
     kuid
    -0.07
    POSITIVE LOGITS
     우리는
    0.12
    情况下
    0.10
     그는
    0.10
     demikian
    0.09
     તેઓ
    0.09
    只有
    0.09
     מדובר
    0.09
    我们
    0.09
    ,《
    0.08
     говорят
    0.08
    Activations Density 0.142%

    No Known Activations