© 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. 69950
    Prev
    Next
    INDEX
    Explanations

    up

    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
     зор
    -0.08
     ор
    -0.08
    ees
    -0.08
    fq
    -0.08
     Graves
    -0.07
     gris
    -0.07
    bard
    -0.07
     Ист
    -0.07
    fz
    -0.07
    slam
    -0.07
    POSITIVE LOGITS
     dith
    0.07
    andie
    0.07
    這
    0.07
    距
    0.07
    _PRESENT
    0.07
    目前
    0.07
    redentials
    0.07
     educated
    0.07
    ilis
    0.07
     Bany
    0.07
    Activations Density 0.005%

    No Known Activations