© 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. 11-RESID-POST-AA
    11. 26382
    Prev
    Next
    INDEX
    Explanations

    powerpoint slides

    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
     Friendship
    -0.08
     prevención
    -0.08
     sinto
    -0.08
     Tween
    -0.08
     cooperación
    -0.08
     partículas
    -0.08
     ecstatic
    -0.08
     collided
    -0.08
     aprendiz
    -0.08
     hydrochlor
    -0.08
    POSITIVE LOGITS
    摘要
    0.12
     presentation
    0.12
     stakeholders
    0.12
     stakeholder
    0.12
     презента
    0.12
     प्रस्त
    0.11
     executives
    0.11
     concise
    0.11
     executive
    0.11
     presentatie
    0.11
    Activations Density 0.043%

    No Known Activations