© 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. 68080
    Prev
    Next
    INDEX
    Explanations

    mediation

    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
     நிறுவ
    -0.08
    igger
    -0.08
     প্রতিষ্ঠ
    -0.08
    ekele
    -0.07
     diap
    -0.07
    ுகள்
    -0.07
    ிகள்
    -0.07
    ieën
    -0.07
     Gupta
    -0.07
     earthly
    -0.07
    POSITIVE LOGITS
     filosofia
    0.10
     philosophie
    0.08
     filosof
    0.08
    岡
    0.08
     philosophy
    0.08
    Preparation
    0.08
    svc
    0.08
     Philosophy
    0.08
     realizada
    0.07
    Cancelled
    0.07
    Activations Density 0.003%

    No Known Activations