© 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. 68344
    Prev
    Next
    INDEX
    Explanations

    assistance

    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
    werte
    -0.08
     ervoor
    -0.08
    سم
    -0.08
     haste
    -0.08
     نیز
    -0.07
    {};↵
    -0.07
     بسیار
    -0.07
     mukaan
    -0.07
     ozna
    -0.07
    IMPORT
    -0.07
    POSITIVE LOGITS
     everyday
    0.08
    /how
    0.07
     саме
    0.07
    점을
    0.07
     overcoming
    0.07
     barədə
    0.07
    erit
    0.07
     وكيف
    0.07
     obwohl
    0.07
     вэ
    0.07
    Activations Density 0.081%

    No Known Activations