© 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 EvalsExportsAPI 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. 113634
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     pathways
    -0.08
     scattering
    -0.08
     Haut
    -0.07
    .
    -0.07
     supporting
    -0.07
     traces
    -0.07
    _blog
    -0.07
    .↵↵
    -0.07
     working
    -0.07
     concerns
    -0.06
    POSITIVE LOGITS
     crescente
    0.12
     increasingly
    0.12
     creciente
    0.11
     نام
    0.10
     Increasing
    0.10
     zunehm
    0.10
     troll
    0.10
     semakin
    0.10
     naam
    0.10
    越来越
    0.10
    Activations Density 0.061%

    No Known Activations