© 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. 94534
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and punctuation

    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
     employ
    -0.07
    iy
    -0.07
    LOGY
    -0.07
     том
    -0.07
    (log
    -0.07
    <|reserved_200016|>
    -0.07
    指导
    -0.07
    <|endoftext|>
    -0.06
    甚至
    -0.06
    оби
    -0.06
    POSITIVE LOGITS
     nối
    0.08
    	short
    0.08
    (?)
    0.08
    ],↵
    0.07
     specials
    0.07
     overshadow
    0.07
    Claire
    0.07
     Gilbert
    0.07
     været
    0.07
    ]},↵
    0.07
    Activations Density 0.014%

    No Known Activations