© 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. 18682
    Prev
    Next
    INDEX
    Explanations

    say "below, we"

    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
     عندما
    -0.13
     যখন
    -0.13
     cuando
    -0.11
     ketika
    -0.11
     quando
    -0.11
     যদি
    -0.11
     όταν
    -0.11
     when
    -0.10
     જ્યારે
    -0.10
    Cuando
    -0.10
    POSITIVE LOGITS
     I'll
    0.12
     we'll
    0.12
     մենք
    0.11
     मैं
    0.11
     espero
    0.10
     найдете
    0.10
     Waxaan
    0.10
     אנו
    0.10
     мы
    0.10
     ನಾನು
    0.10
    Activations Density 0.008%

    No Known Activations