© 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. 50740
    Prev
    Next
    INDEX
    Explanations

    we

    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
     voulait
    -0.10
     wollte
    -0.10
     semblait
    -0.10
     mattered
    -0.09
     wants
    -0.09
     Wants
    -0.09
     intends
    -0.09
    wanted
    -0.09
     prévoit
    -0.09
     parecía
    -0.09
    POSITIVE LOGITS
     lack
    0.35
     Lack
    0.30
     lacks
    0.28
     lacking
    0.28
    lack
    0.24
     lacked
    0.24
    缺
    0.24
     gebrek
    0.23
     falta
    0.23
     manque
    0.21
    Activations Density 0.066%

    No Known Activations