© 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. 110933
    Prev
    Next
    INDEX
    Explanations

    time period

    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
     Miche
    -0.08
     REAL
    -0.07
     reale
    -0.07
    panel
    -0.07
    Deb
    -0.07
     Deb
    -0.07
     понят
    -0.07
     Gas
    -0.07
     Brussel
    -0.07
     réal
    -0.07
    POSITIVE LOGITS
     corresponds
    0.09
     인해
    0.08
     corresponde
    0.08
    च
    0.08
     തന്നെ
    0.07
     vực
    0.07
     entspricht
    0.07
     bahwa
    0.07
     muud
    0.07
    �
    0.07
    Activations Density 0.049%

    No Known Activations