© 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. 110439
    Prev
    Next
    INDEX
    Explanations

    code, api keys

    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
     מוצ
    -0.10
    重量
    -0.09
     buscas
    -0.08
    ubon
    -0.08
     commemorate
    -0.08
     commemor
    -0.08
     памят
    -0.08
     embellished
    -0.08
     suspe
    -0.08
     insol
    -0.08
    POSITIVE LOGITS
    _TOKEN
    0.10
     token
    0.10
     TOKEN
    0.09
    OAuth
    0.09
    token
    0.09
    OKEN
    0.09
    _token
    0.09
    Token
    0.09
     config
    0.09
    TOKEN
    0.09
    Activations Density 0.002%

    No Known Activations