© 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. 70046
    Prev
    Next
    INDEX
    Explanations

    historical periods

    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
     Solaris
    -0.08
     سين
    -0.08
     bons
    -0.08
     Wonderland
    -0.07
     easily
    -0.07
     Bedroom
    -0.07
    երս
    -0.07
     dropdown
    -0.07
     grapefruit
    -0.07
     waveform
    -0.07
    POSITIVE LOGITS
     tätig
    0.08
     les
    0.08
     kilomètres
    0.08
     thee
    0.07
     બન
    0.07
    _K
    0.07
     calculating
    0.07
     changement
    0.07
     रहल
    0.07
    ogene
    0.07
    Activations Density 0.000%

    No Known Activations