© 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. 129289
    Prev
    Next
    INDEX
    Explanations

    use

    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
     그런데
    -0.09
     나
    -0.09
    Disp
    -0.09
     Disp
    -0.08
     dispersion
    -0.08
    disp
    -0.08
    _binding
    -0.08
     യുവ
    -0.08
     относ
    -0.08
    509
    -0.07
    POSITIVE LOGITS
    (constants
    0.09
     Ys
    0.08
     Moto
    0.08
     toer
    0.08
     Morr
    0.08
     econ
    0.08
     mend
    0.08
    utm
    0.07
    /ac
    0.07
     ape
    0.07
    Activations Density 0.001%

    No Known Activations