© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1107
    Prev
    Next
    INDEX
    Explanations

    relevancy

    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
     überw
    -0.08
    349
    -0.08
     �
    -0.07
     priests
    -0.07
     Schwarz
    -0.07
    -operated
    -0.07
    ole
    -0.07
    essional
    -0.07
     separado
    -0.07
    晶
    -0.07
    POSITIVE LOGITS
     banget
    0.08
     кур
    0.08
     honoring
    0.08
     nex
    0.08
     sacrificing
    0.08
     intitul
    0.08
     ومت
    0.08
    กับ
    0.08
     Ju
    0.07
    hon
    0.07
    Activations Density 0.012%

    No Known Activations