© 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. 111050
    Prev
    Next
    INDEX
    Explanations

    Math multiplication 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
     takim
    -0.09
     Flugh
    -0.08
     adres
    -0.08
    binations
    -0.08
     лечении
    -0.08
     sente
    -0.08
    \Fac
    -0.08
     farewell
    -0.08
    parking
    -0.07
     samoch
    -0.07
    POSITIVE LOGITS
     further
    0.09
     super
    0.08
    rops
    0.07
    Further
    0.07
    ása
    0.07
     ಕೈ
    0.07
     leads
    0.07
    进一步
    0.07
     Further
    0.07
     involves
    0.07
    Activations Density 0.031%

    No Known Activations