© 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. 95464
    Prev
    Next
    INDEX
    Explanations

    得

    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
     yu
    -0.08
    ป์
    -0.08
     Yu
    -0.08
    agay
    -0.07
    oines
    -0.07
     стоимость
    -0.07
     assisted
    -0.07
     deseas
    -0.07
    ion
    -0.07
    	cursor
    -0.07
    POSITIVE LOGITS
    Pun
    0.08
     récomp
    0.08
    imeters
    0.08
     phép
    0.07
    体现
    0.07
     संच
    0.07
     recompensa
    0.07
    SCH
    0.07
    erek
    0.07
     ساق
    0.07
    Activations Density 0.003%

    No Known Activations