© 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 EvalsExportsAPI 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. 49865
    Prev
    Next
    INDEX
    Explanations

    an

    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
     difíciles
    -0.08
     kuhusu
    -0.08
    ριθ
    -0.08
     gh
    -0.08
     çıkt
    -0.08
     gars
    -0.08
     leid
    -0.08
     noter
    -0.08
     numpy
    -0.08
     chuid
    -0.08
    POSITIVE LOGITS
    álise
    0.19
    alisar
    0.13
    ál
    0.12
    cor
    0.11
    ális
    0.11
    ed
    0.10
    jo
    0.10
    inh
    0.09
    ônimo
    0.09
    álogo
    0.09
    Activations Density 0.000%

    No Known Activations