© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47181
    Prev
    Next
    INDEX
    Explanations

    Mob

    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
     neu
    -0.08
     Judy
    -0.08
     Chu
    -0.07
     syst
    -0.07
     Ceremony
    -0.07
     ensayo
    -0.07
     Sisters
    -0.07
    型号
    -0.07
     Humanities
    -0.07
    ,num
    -0.07
    POSITIVE LOGITS
     indebted
    0.08
     reduc
    0.08
     eat
    0.07
     praying
    0.07
     prison
    0.07
     locally
    0.07
     rédu
    0.07
     slaughter
    0.07
     بناء
    0.07
     Regulation
    0.07
    Activations Density 0.002%

    No Known Activations