© 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. 23-RESID-POST-AA
    11. 51517
    Prev
    Next
    INDEX
    Explanations

    TV networks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profesores
    -0.08
     legislators
    -0.08
     පො
    -0.08
     inventories
    -0.08
    -webpack
    -0.08
     Governors
    -0.08
     الوز
    -0.08
     manifi
    -0.08
    ̂
    -0.07
     webmaster
    -0.07
    POSITIVE LOGITS
     Fox
    0.14
     Sky
    0.13
     TNT
    0.12
    Fox
    0.11
     Channel
    0.11
     FOX
    0.11
     canales
    0.11
     CNBC
    0.11
    天空
    0.11
     canais
    0.11
    Activations Density 0.007%

    No Known Activations