© 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. 19-RESID-POST-AA
    11. 103326
    Prev
    Next
    INDEX
    Explanations

    so, then

    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
     Hvis
    -0.10
    ourced
    -0.09
     если
    -0.09
     Якщо
    -0.09
     إذا
    -0.09
     หาก
    -0.09
     karena
    -0.09
     Jeśli
    -0.09
    因为
    -0.09
     since
    -0.09
    POSITIVE LOGITS
     substitute
    0.12
    :↵↵
    0.10
     equations
    0.10
     equation
    0.10
     compute
    0.10
     expression
    0.10
    Compute
    0.09
     calculate
    0.09
     substitution
    0.09
    ：↵↵
    0.09
    Activations Density 0.032%

    No Known Activations