© 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. 95027
    Prev
    Next
    INDEX
    Explanations

    bell

    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
    abcdefghijklmnopqrstuvwxyz
    -0.08
     paved
    -0.07
     engineered
    -0.07
    兒
    -0.07
     speciality
    -0.07
    타
    -0.07
    _checkbox
    -0.06
     ребенка
    -0.06
     yung
    -0.06
    警方
    -0.06
    POSITIVE LOGITS
     Shoulder
    0.10
     saute
    0.09
     sauté
    0.09
     Drop
    0.08
     �
    0.08
     impe
    0.08
     तेल
    0.08
     модел
    0.08
     shoulder
    0.08
     {.
    0.08
    Activations Density 0.002%

    No Known Activations