© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 7861
    Prev
    Next
    INDEX
    Explanations

    financial calculations

    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
    raid
    -0.08
     palate
    -0.08
     való
    -0.08
     enclave
    -0.07
    ová
    -0.07
     tastes
    -0.07
     adjacent
    -0.07
    Dragon
    -0.07
     capture
    -0.07
     concat
    -0.07
    POSITIVE LOGITS
     Worked
    0.10
     જાણવા
    0.10
     հետև
    0.10
     Formel
    0.09
     پوچھ
    0.09
     qanoq
    0.09
     հաշվ
    0.09
     որոն
    0.09
     տոկոս
    0.09
     incó
    0.09
    Activations Density 0.118%

    No Known Activations