© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1430
    Prev
    Next
    INDEX
    Explanations

    invoice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fasc
    -0.08
    כל
    -0.08
    委员
    -0.08
     Schl
    -0.07
     ර
    -0.07
     rück
    -0.07
     doel
    -0.07
    ിരുന്നു
    -0.07
     ej
    -0.07
     samm
    -0.07
    POSITIVE LOGITS
     shipped
    0.08
     deducted
    0.08
    цю
    0.08
     issued
    0.08
     £
    0.08
     outsourcing
    0.08
     pragmatic
    0.08
    金额
    0.07
    vic
    0.07
    bled
    0.07
    Activations Density 0.003%

    No Known Activations