© 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. 78242
    Prev
    Next
    INDEX
    Explanations

    Redis

    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
     भीतर
    -0.09
     antagonist
    -0.08
    inp
    -0.08
    cretsiz
    -0.08
    ytte
    -0.08
     depr
    -0.08
     Within
    -0.08
     الداخلية
    -0.07
     Freib
    -0.07
     żad
    -0.07
    POSITIVE LOGITS
     connection
    0.10
     connectivity
    0.09
    _connection
    0.09
     integration
    0.09
    Connection
    0.08
     conect
    0.08
     integriert
    0.08
    .enabled
    0.08
    _conn
    0.08
    .connect
    0.08
    Activations Density 0.015%

    No Known Activations