© 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. 79023
    Prev
    Next
    INDEX
    Explanations

    logic, math

    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
     Fah
    -0.08
     relacionados
    -0.07
     Lucas
    -0.07
    혹
    -0.07
     dolores
    -0.07
     niveau
    -0.07
     nivå
    -0.07
     niveles
    -0.07
    ړ
    -0.07
    _holder
    -0.07
    POSITIVE LOGITS
    wards
    0.16
    ward
    0.13
     бағыт
    0.10
     दिशा
    0.10
    WARD
    0.10
    方向
    0.10
     напрям
    0.10
     вверх
    0.10
     направления
    0.09
     방향
    0.09
    Activations Density 0.036%

    No Known Activations