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. 15-RESID-POST-AA
    6. 19498
    Prev
    Next
    INDEX
    Explanations

    11

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     پس
    -0.08
    /src
    -0.08
     Core
    -0.08
    =@
    -0.08
    /@
    -0.08
     gutter
    -0.07
     @
    -0.07
    /Button
    -0.07
    /CD
    -0.07
     ഫോ
    -0.07
    POSITIVE LOGITS
     Amerika
    0.08
     mira
    0.08
    0.08
     atmosphere
    0.08
    ируют
    0.07
    促进
    0.07
    enteel
    0.07
     procesos
    0.07
     puntos
    0.07
     доставка
    0.07
    Activations Density 0.003%

    No Known Activations