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. 88031
    Prev
    Next
    INDEX
    Explanations

    Game movement/actions

    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
    ब
    -0.07
    ைவ
    -0.07
     eventual
    -0.07
    ाई
    -0.07
     conspiracy
    -0.07
     Barat
    -0.07
    .reader
    -0.07
    Lear
    -0.07
     unravel
    -0.07
    Master
    -0.06
    POSITIVE LOGITS
     reposition
    0.09
     μία
    0.09
     Flexible
    0.09
     déplacement
    0.09
     voluntarily
    0.09
     déplacer
    0.08
     inos
    0.08
     illegally
    0.08
     nō
    0.08
     NOM
    0.08
    Activations Density 0.012%

    No Known Activations