© 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. 110529
    Prev
    Next
    INDEX
    Explanations

    describe

    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
     MOV
    -0.09
    MOV
    -0.08
     MX
    -0.08
    ുകയാണ്
    -0.08
    IVA
    -0.08
     alumn
    -0.08
     mendapatkan
    -0.08
     жизн
    -0.08
    คือ
    -0.08
    омним
    -0.07
    POSITIVE LOGITS
     clutter
    0.08
     excessive
    0.08
     exceed
    0.08
     embellished
    0.08
     depict
    0.08
     glaring
    0.08
     extravag
    0.08
     лиш
    0.08
    呈
    0.08
     presto
    0.08
    Activations Density 0.003%

    No Known Activations