© 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. 11-RESID-POST-AA
    11. 79149
    Prev
    Next
    INDEX
    Explanations

    Roman history/politics

    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
     QC
    -0.09
     पस
    -0.08
    ేత
    -0.08
     gc
    -0.08
    _gc
    -0.08
     तार
    -0.07
    Gc
    -0.07
     GC
    -0.07
     qc
    -0.07
     porn
    -0.07
    POSITIVE LOGITS
     blocker
    0.09
     blockers
    0.09
     catalyst
    0.08
     shp
    0.08
     حماية
    0.08
     abolition
    0.08
    축
    0.07
     sluit
    0.07
     RH
    0.07
     provocar
    0.07
    Activations Density 0.000%

    No Known Activations