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. 44809
    Prev
    Next
    INDEX
    Explanations

    cooperatives

    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
     plane
    -0.08
     Plane
    -0.08
    Plane
    -0.08
     Spare
    -0.08
    快
    -0.08
     способности
    -0.07
     содерж
    -0.07
     distraction
    -0.07
     Maße
    -0.07
     eu
    -0.07
    POSITIVE LOGITS
    -owned
    0.10
    Ownership
    0.10
    ownership
    0.09
    -Owned
    0.09
     ownership
    0.09
     grassroots
    0.09
    旗下
    0.09
     empowerment
    0.08
    _owned
    0.08
     Ownership
    0.08
    Activations Density 0.007%

    No Known Activations