© 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. 13167
    Prev
    Next
    INDEX
    Explanations

    doing

    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
     Census
    -0.09
     census
    -0.08
     Ash
    -0.07
    法律
    -0.07
    作用
    -0.07
     useless
    -0.07
    -0.07
     Cleaning
    -0.07
     Potential
    -0.07
    te
    -0.07
    POSITIVE LOGITS
    さん
    0.09
     인
    0.08
     Loh
    0.08
     lohnt
    0.08
     kunsten
    0.08
    인을
    0.08
    0.08
     folgt
    0.08
     svého
    0.08
     Bryan
    0.07
    Activations Density 0.024%
    No Known Activations