© 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. 47881
    Prev
    Next
    INDEX
    Explanations

    Detecting mathematical errors

    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
     हाई
    -0.08
     empathy
    -0.08
    Dank
    -0.07
    Gradu
    -0.07
    Perg
    -0.07
     veg
    -0.07
     vista
    -0.07
     geh
    -0.07
     deline
    -0.07
     cooperative
    -0.07
    POSITIVE LOGITS
     discrepancies
    0.11
     inconsistent
    0.11
     inconsist
    0.10
    との
    0.10
     discrepancy
    0.10
     incons
    0.10
     disag
    0.10
     discrep
    0.10
     невер
    0.10
     conflicting
    0.10
    Activations Density 0.050%

    No Known Activations