© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    null

    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
     Faust
    -0.08
     bye
    -0.08
    الإ
    -0.08
     Swan
    -0.08
     zipped
    -0.08
     �
    -0.08
    incs
    -0.07
     remainder
    -0.07
    이를
    -0.07
    गळ
    -0.07
    POSITIVE LOGITS
     XT
    0.08
     Kam
    0.08
    xt
    0.08
    put
    0.08
     vastly
    0.07
    stream
    0.07
     Baron
    0.07
    station
    0.07
    enje
    0.07
    wort
    0.07
    Activations Density 0.001%

    No Known Activations