© 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 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. 69759
    Prev
    Next
    INDEX
    Explanations

    可

    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
     یک
    -0.08
     دائ
    -0.08
     trí
    -0.08
     một
    -0.08
     trg
    -0.08
     arra
    -0.07
     stets
    -0.07
     دائم
    -0.07
     luôn
    -0.07
     beig
    -0.07
    POSITIVE LOGITS
    Nuevo
    0.08
     disadvantages
    0.08
    -controlled
    0.08
     MORE
    0.08
     EVERYTHING
    0.08
     disadvantage
    0.07
    şg
    0.07
    福建
    0.07
    -new
    0.07
     olduğunu
    0.07
    Activations Density 0.001%

    No Known Activations