Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52861
    Prev
    Next
    INDEX
    Explanations

    Order or sequence

    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
     Thy
    -0.08
     מטר
    -0.08
     περί
    -0.08
     Ort
    -0.07
     >=
    -0.07
     yolu
    -0.07
    .ONE
    -0.07
     aşa
    -0.07
     עוב
    -0.07
     структура
    -0.07
    POSITIVE LOGITS
     появления
    0.11
     tiempos
    0.10
     시간이
    0.10
     출시
    0.10
     arrivals
    0.10
     времени
    0.10
     virtue
    0.10
     时间
    0.10
     aconteceu
    0.09
     acontecer
    0.09
    Activations Density 0.011%

    No Known Activations