© 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. 69387
    Prev
    Next
    INDEX
    Explanations

    GPT

    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
     nicely
    -0.08
     tem
    -0.07
    ın
    -0.07
     behaviors
    -0.07
     ta
    -0.07
    inke
    -0.07
     TEM
    -0.07
    Here's
    -0.07
    =find
    -0.07
     specified
    -0.07
    POSITIVE LOGITS
     Unable
    0.10
    无法
    0.10
     evac
    0.09
     unaware
    0.09
     обеспечение
    0.09
     pouze
    0.09
    ですが
    0.09
     incapable
    0.08
    不知道
    0.08
     inability
    0.08
    Activations Density 0.005%

    No Known Activations