© 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. 63755
    Prev
    Next
    INDEX
    Explanations

    top portion being cut

    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
     പര
    -0.08
    ，
    -0.07
    NA
    -0.07
    iksi
    -0.07
     கொள்ள
    -0.07
    adores
    -0.07
    ，在
    -0.07
     അത
    -0.07
     כדי
    -0.07
    ，不过
    -0.07
    POSITIVE LOGITS
     portions
    0.10
    قه
    0.10
     Portions
    0.10
     southwest
    0.09
    geteilt
    0.09
     northwest
    0.09
     droit
    0.09
     southwestern
    0.09
     southern
    0.09
     Portion
    0.09
    Activations Density 0.020%

    No Known Activations