© 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. 68196
    Prev
    Next
    INDEX
    Explanations

    31

    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
     التر
    -0.09
     Melhor
    -0.08
    �
    -0.08
    uphoria
    -0.08
     sobrem
    -0.07
     Empfang
    -0.07
    uptools
    -0.07
     abus
    -0.07
     filtering
    -0.07
     વધારો
    -0.07
    POSITIVE LOGITS
    †
    0.08
    dag
    0.08
    placement
    0.08
     जस
    0.08
    Placement
    0.08
     wasm
    0.08
     Checklist
    0.07
    graf
    0.07
    .Session
    0.07
     புத்த
    0.07
    Activations Density 0.002%

    No Known Activations