© 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. 26222
    Prev
    Next
    INDEX
    Explanations

    folder

    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
     사
    -0.10
     مرا
    -0.07
     �
    -0.07
     Pierre
    -0.07
     zk
    -0.07
     Elk
    -0.07
     truthful
    -0.07
     unders
    -0.07
     fle
    -0.07
     وب
    -0.07
    POSITIVE LOGITS
     Cil
    0.08
    hands
    0.07
    /The
    0.07
     Banks
    0.07
    /File
    0.07
    里的
    0.07
     SOP
    0.07
     blessing
    0.07
    ’S
    0.07
    indic
    0.07
    Activations Density 0.005%

    No Known Activations