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. 43410
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    underline
    -0.08
    ovar
    -0.08
    Exceptional
    -0.08
     slut
    -0.08
    �
    -0.07
    mente
    -0.07
    onies
    -0.07
     tiled
    -0.07
    ्यात
    -0.07
    -wife
    -0.07
    POSITIVE LOGITS
     Sou
    0.08
     аэроп
    0.08
    0.08
     источник
    0.08
     прям
    0.07
     محت
    0.07
     провед
    0.07
     �
    0.07
    .super
    0.07
     draw
    0.07
    Activations Density 0.018%

    No Known Activations