© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113654
    Prev
    Next
    INDEX
    Explanations

    le

    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
     Sm
    -0.09
    _CLR
    -0.08
    -liquid
    -0.08
     Hungry
    -0.08
    dien
    -0.08
    orang
    -0.08
     пи
    -0.07
     нек
    -0.07
    -clock
    -0.07
    conce
    -0.07
    POSITIVE LOGITS
     demeanor
    0.10
    -hearted
    0.09
    hearted
    0.09
     reminder
    0.09
    🏼
    0.08
    厚
    0.08
    ROS
    0.08
     Wal
    0.08
     regimen
    0.08
     diẹ
    0.08
    Activations Density 0.008%

    No Known Activations