© 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. 11-RESID-POST-AA
    11. 113393
    Prev
    Next
    INDEX
    Explanations

    code with numbers/strings

    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
    ುತ್ತ
    -0.08
     оборудование
    -0.08
    ುತ್ತಾರೆ
    -0.08
    绩
    -0.08
    巡视
    -0.07
    OLUMNS
    -0.07
    ಾಮಿ
    -0.07
    ಕ್ತಿ
    -0.07
    担当
    -0.07
     alm
    -0.07
    POSITIVE LOGITS
     Empty
    0.10
    Empty
    0.09
    empty
    0.08
     EMPTY
    0.08
     malformed
    0.08
    Malformed
    0.08
     Larger
    0.08
    EMPTY
    0.08
     Ср
    0.08
    _empty
    0.08
    Activations Density 0.009%

    No Known Activations