© 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. 21583
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ങ്ങളിലും
    -0.09
    වත්
    -0.08
     אפילו
    -0.08
    Colours
    -0.08
     жет
    -0.08
    наче
    -0.08
     majd
    -0.08
    ങ്ങളും
    -0.08
    દ્ધ
    -0.08
     તેવી
    -0.08
    POSITIVE LOGITS
     derivative
    0.13
     with
    0.12
     is
    0.12
     yields
    0.12
     involves
    0.11
     dx
    0.10
     derivatives
    0.10
    Derivative
    0.10
     avec
    0.10
     gives
    0.10
    Activations Density 0.010%

    No Known Activations