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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111476
    Prev
    Next
    INDEX
    Explanations

    2

    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
    akir
    -0.07
    Vak
    -0.07
     inertia
    -0.07
     الو
    -0.07
     какая
    -0.07
    Reliable
    -0.07
     sme
    -0.07
    .annotations
    -0.07
    _annotations
    -0.07
     continuity
    -0.07
    POSITIVE LOGITS
    clamation
    0.08
    」、「
    0.08
     Kumar
    0.08
     Royaume
    0.08
     Ts
    0.07
     Lets
    0.07
    imeter
    0.07
     আ
    0.07
     Sons
    0.07
     ټول
    0.07
    Activations Density 0.004%

    No Known Activations