© 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. 13416
    Prev
    Next
    INDEX
    Explanations

    L or Return

    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
    ELS
    -0.09
     elong
    -0.08
    elt
    -0.08
    issima
    -0.08
     ene
    -0.07
    ateur
    -0.07
    padding
    -0.07
    Cover
    -0.07
    Editable
    -0.07
    -cover
    -0.07
    POSITIVE LOGITS
     Ankara
    0.08
     над
    0.08
     ona
    0.08
    判
    0.08
     Bell
    0.08
     Quarter
    0.07
    .mk
    0.07
     Mex
    0.07
     Quarterly
    0.07
     Spectrum
    0.07
    Activations Density 0.000%

    No Known Activations