© 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. 79297
    Prev
    Next
    INDEX
    Explanations

    database keys and partitioning

    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
     Bow
    -0.08
    үз
    -0.08
    敢
    -0.08
    Bow
    -0.08
     recession
    -0.07
     Dres
    -0.07
    成人视频
    -0.07
    brev
    -0.07
    пион
    -0.07
    nict
    -0.07
    POSITIVE LOGITS
     hashing
    0.11
    .hash
    0.11
     hash
    0.10
     hashed
    0.10
     determinar
    0.10
    (hash
    0.10
    	hash
    0.09
     Determ
    0.09
     modulo
    0.09
     결정
    0.09
    Activations Density 0.006%

    No Known Activations