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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91109
    Prev
    Next
    INDEX
    Explanations

    ||

    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
     nau
    -0.09
     dyl
    -0.08
     Zeitpunkt
    -0.08
    _notify
    -0.08
     наз
    -0.07
     oportun
    -0.07
     bully
    -0.07
    壮
    -0.07
     naz
    -0.07
     Skate
    -0.07
    POSITIVE LOGITS
    ISO
    0.08
    message
    0.07
    Tum
    0.07
    binder
    0.07
     IT
    0.07
    IT
    0.07
     Sø
    0.07
     eight
    0.07
    roger
    0.07
    App
    0.07
    Activations Density 0.016%

    No Known Activations