© 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. 69490
    Prev
    Next
    INDEX
    Explanations

    geometric ratio problems

    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
     incorpor
    -0.08
     gen
    -0.08
     werkelijkheid
    -0.08
     endemic
    -0.07
     uitdag
    -0.07
     वास्तव
    -0.07
     Lib
    -0.07
     alty
    -0.07
    Authentication
    -0.07
     altura
    -0.07
    POSITIVE LOGITS
     mardi
    0.08
    (machine
    0.08
     nitori
    0.07
    gaon
    0.07
    ્રણ
    0.07
    rown
    0.07
    .quest
    0.07
    kep
    0.07
    96
    0.07
     sinus
    0.07
    Activations Density 0.000%

    No Known Activations