© 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. 64892
    Prev
    Next
    INDEX
    Explanations

    int, float data types

    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
     HAS
    -0.08
    福利
    -0.08
     WT
    -0.08
     bem
    -0.08
     wellbeing
    -0.08
     lentamente
    -0.08
    奉
    -0.07
    ตลาด
    -0.07
    لاء
    -0.07
     సందర్భంగా
    -0.07
    POSITIVE LOGITS
     numériques
    0.10
    /string
    0.09
     numérique
    0.09
    .Integer
    0.09
    .Array
    0.09
    ophy
    0.08
    prototype
    0.08
    Convertible
    0.08
     prototypes
    0.08
    .String
    0.08
    Activations Density 0.011%

    No Known Activations