© 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. 91837
    Prev
    Next
    INDEX
    Explanations

    to

    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
     영향
    -0.08
     hany
    -0.07
     geta
    -0.07
     fas
    -0.07
     pon
    -0.07
    -tier
    -0.07
     진
    -0.07
    객
    -0.07
     матер
    -0.07
    ətli
    -0.07
    POSITIVE LOGITS
     [-]:
    0.08
     Login
    0.08
     metabol
    0.08
    uge
    0.08
    	W
    0.07
    +:
    0.07
     स्ल
    0.07
    .Cancel
    0.07
     west
    0.07
     desl
    0.07
    Activations Density 0.000%

    No Known Activations