© 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. 3-RESID-POST-AA
    11. 13322
    Prev
    Next
    INDEX
    Explanations

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đề
    -0.08
     trips
    -0.07
     restructure
    -0.07
    席
    -0.07
     reflecting
    -0.07
     tris
    -0.07
     doubles
    -0.07
    itzar
    -0.07
     sprach
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Burr
    0.08
    נן
    0.08
     evapor
    0.08
     Phillies
    0.08
    stab
    0.08
    夹
    0.08
     clam
    0.08
    (et
    0.08
    _stamp
    0.08
     Nor
    0.08
    Activations Density 0.074%

    No Known Activations