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. 109663
    Prev
    Next
    INDEX
    Explanations

    read

    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
    ilot
    -0.09
     נמצא
    -0.08
    kus
    -0.08
     لذلك
    -0.08
    yan
    -0.08
     Sty
    -0.08
     تلك
    -0.08
     שפ
    -0.07
     Intelligent
    -0.07
    steel
    -0.07
    POSITIVE LOGITS
     dificil
    0.09
    ېد
    0.08
     aloud
    0.08
    扑
    0.08
    ઉ
    0.07
    棒
    0.07
    цё
    0.07
    :(
    0.07
    (draw
    0.07
    读
    0.07
    Activations Density 0.007%

    No Known Activations