© 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. 19-RESID-POST-AA
    11. 18995
    Prev
    Next
    INDEX
    Explanations

    about

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     российского
    -0.09
    由
    -0.09
    Among
    -0.09
     ถูก
    -0.08
     provenant
    -0.08
     Among
    -0.08
    shenziswa
    -0.08
     pakati
    -0.08
     используются
    -0.08
     između
    -0.08
    POSITIVE LOGITS
     بشأن
    0.16
     regarding
    0.15
     bezüglich
    0.15
    关于
    0.14
     ofreci
    0.13
     whom
    0.13
     about
    0.12
     mengenai
    0.12
     concernant
    0.12
     درباره
    0.12
    Activations Density 0.080%

    No Known Activations