© 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. 70083
    Prev
    Next
    INDEX
    Explanations

    of

    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
    俱
    -0.08
    ochemical
    -0.08
    ierter
    -0.07
    argar
    -0.07
    zier
    -0.07
     اظ
    -0.07
     Grupo
    -0.07
    鼻
    -0.07
     Italien
    -0.07
    િત
    -0.07
    POSITIVE LOGITS
     này
    0.10
     wybor
    0.08
    টির
    0.08
     cop
    0.07
     назначения
    0.07
     MCP
    0.07
     ours
    0.07
     chiqar
    0.07
     drew
    0.07
     gh
    0.07
    Activations Density 0.040%

    No Known Activations