© 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. 31374
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    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
    当に
    -0.08
     paradigm
    -0.07
     aṣ
    -0.07
     retention
    -0.07
    afr
    -0.07
     stuff
    -0.07
     asked
    -0.07
     dire
    -0.07
     regimen
    -0.07
    Dire
    -0.07
    POSITIVE LOGITS
    ，因此
    0.12
    。在
    0.11
    ，使
    0.11
    ，在
    0.11
     لذا
    0.11
    。不
    0.10
    。また
    0.10
    ，例如
    0.10
    ，并
    0.10
    。この
    0.10
    Activations Density 0.071%

    No Known Activations