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

    Neuronpedia

    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. 75786
    Prev
    Next
    INDEX
    Explanations

    Bubbles

    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
    eller
    -0.08
     guida
    -0.08
    Library
    -0.07
    TLS
    -0.07
     mold
    -0.07
    Lincoln
    -0.07
    ırı
    -0.07
    교
    -0.07
    Ram
    -0.07
     infinitely
    -0.07
    POSITIVE LOGITS
     Casc
    0.11
     propagation
    0.10
     Bubble
    0.10
     bubbles
    0.10
    _DOWN
    0.09
     casc
    0.09
     upwards
    0.09
    Propagation
    0.09
    传播
    0.09
     cascading
    0.09
    Activations Density 0.001%

    No Known Activations