© 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. 19
    Prev
    Next
    INDEX
    Explanations

    foreign exchange/monetary policy

    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
    -nine
    -0.09
     Timing
    -0.09
     =================================================================
    -0.09
     genial
    -0.09
    Hoi
    -0.09
    Timing
    -0.09
     vooruit
    -0.08
    .sound
    -0.08
     cocina
    -0.08
     Cocina
    -0.08
    POSITIVE LOGITS
     supervised
    0.08
     support
    0.08
     comprom
    0.07
     desired
    0.07
    imbal
    0.07
     TF
    0.07
    זרת
    0.07
     interventions
    0.07
     suffice
    0.07
     вруч
    0.07
    Activations Density 0.005%

    No Known Activations