© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99288
    Prev
    Next
    INDEX
    Explanations

    until

    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
     täglichen
    -0.09
    机关
    -0.09
     ainult
    -0.08
     Subsid
    -0.08
     "=
    -0.08
     Ayuntamiento
    -0.08
     Ending
    -0.08
    ，就是
    -0.08
    /null
    -0.08
     Navarro
    -0.08
    POSITIVE LOGITS
     fragrant
    0.08
     US
    0.07
     рак
    0.07
     vital
    0.07
    OIN
    0.07
     તેમ
    0.07
    成熟
    0.07
    够
    0.07
     dour
    0.07
     fascinating
    0.07
    Activations Density 0.006%

    No Known Activations