© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44865
    Prev
    Next
    INDEX
    Explanations

    Homer's Iliad excerpts

    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
     Simpl
    -0.09
     简
    -0.09
    Simpl
    -0.08
     Current
    -0.08
     模
    -0.08
    .current
    -0.08
     simplifies
    -0.08
     afirma
    -0.08
    Simulator
    -0.08
     simplified
    -0.07
    POSITIVE LOGITS
     wrath
    0.09
     boast
    0.08
     quas
    0.08
     sorrow
    0.08
    apart
    0.08
     Zeus
    0.08
     indirectly
    0.07
    #ifdef
    0.07
    ae
    0.07
     divine
    0.07
    Activations Density 0.024%

    No Known Activations