© 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. 54727
    Prev
    Next
    INDEX
    Explanations

    family systems therapy

    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
     steak
    -0.09
    /Table
    -0.08
     IEnumerable
    -0.08
     blue
    -0.07
     shk
    -0.07
    /ge
    -0.07
    689
    -0.07
     자료
    -0.07
     Tables
    -0.07
     જવ
    -0.07
    POSITIVE LOGITS
     exces
    0.11
     excessively
    0.10
     excessive
    0.10
     overly
    0.10
     demasiado
    0.10
     demasi
    0.10
    appropr
    0.09
     слишком
    0.09
     healthy
    0.09
    Healthy
    0.09
    Activations Density 0.009%

    No Known Activations