© 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. 3-RESID-POST-AA
    11. 2566
    Prev
    Next
    INDEX
    Explanations

    ged/ges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DY
    -0.09
     DY
    -0.08
    nz
    -0.08
    બંધ
    -0.08
     yab
    -0.07
    Fixture
    -0.07
     facilitates
    -0.07
    CY
    -0.07
     ******
    -0.07
     siz
    -0.07
    POSITIVE LOGITS
    え
    0.09
     calcul
    0.08
     sacrificing
    0.08
     Bosch
    0.07
    calcul
    0.07
    0.07
     pict
    0.07
     grim
    0.07
     Bang
    0.07
     Salem
    0.07
    Activations Density 0.031%

    No Known Activations