© 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. 24747
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Immigration
    -0.08
     hãy
    -0.08
    Pred
    -0.07
    ullu
    -0.07
    _atom
    -0.07
     Sanders
    -0.07
    額
    -0.07
     Pred
    -0.07
     Uni
    -0.07
    opu
    -0.07
    POSITIVE LOGITS
    ง่าย
    0.11
     بسهولة
    0.11
     hästi
    0.10
     যায়
    0.10
    很好
    0.09
    容易
    0.09
     sayesinde
    0.09
     kanjani
    0.09
    _when
    0.09
     যায়
    0.09
    Activations Density 0.090%

    No Known Activations