© 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. 7-RESID-POST-AA
    11. 986
    Prev
    Next
    INDEX
    Explanations

    prompt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ministries
    -0.08
     mow
    -0.08
    先
    -0.07
    વી
    -0.07
     každ
    -0.07
     pursue
    -0.07
     št
    -0.07
     lif
    -0.07
     pastors
    -0.07
    骚
    -0.07
    POSITIVE LOGITS
     पॉ
    0.08
    nis
    0.08
    nez
    0.08
    DAT
    0.08
    вин
    0.07
     ए
    0.07
     मैच
    0.07
     DC
    0.07
    णी
    0.07
     Couldn't
    0.07
    Activations Density 0.006%

    No Known Activations