© 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. 23-RESID-POST-AA
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    say "user"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     modify
    -0.10
    modify
    -0.09
    Modify
    -0.08
    IBM
    -0.08
     IBM
    -0.08
     JMS
    -0.08
     Yas
    -0.08
    Req
    -0.08
     Waik
    -0.08
    .jsp
    -0.08
    POSITIVE LOGITS
    actable
    0.10
    pivot
    0.10
     pivot
    0.09
     Pivot
    0.09
     stripe
    0.09
     polym
    0.09
     microp
    0.09
    Pivot
    0.09
     Stripe
    0.09
    conversation
    0.09
    Activations Density 0.004%

    No Known Activations