© 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. 102498
    Prev
    Next
    INDEX
    Explanations

    geometry reflections

    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
     Certain
    -0.08
     Social
    -0.08
     vissa
    -0.08
     certain
    -0.08
     ciertos
    -0.08
    �
    -0.07
    Há
    -0.07
     Sozial
    -0.07
     bestimmten
    -0.07
    」（
    -0.07
    POSITIVE LOGITS
     becomes
    0.09
     namely
    0.09
     амер
    0.08
     sebesar
    0.08
     magiging
    0.08
     become
    0.08
     then
    0.08
     буде
    0.08
     ապա
    0.08
    wile
    0.08
    Activations Density 0.067%

    No Known Activations