© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110627
    Prev
    Next
    INDEX
    Explanations

    Roles/tasks or assignments

    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
     സ്വകാര്യ
    -0.09
    ateness
    -0.08
     evokes
    -0.08
     maken
    -0.08
     //$
    -0.08
     evoke
    -0.08
     tb
    -0.08
    IGIN
    -0.08
     propria
    -0.07
     privaten
    -0.07
    POSITIVE LOGITS
    负责
    0.14
     complementary
    0.09
     teamwork
    0.09
     duo
    0.09
    Needed
    0.09
    Responsibilities
    0.09
     responsibilities
    0.09
     aporta
    0.09
    职责
    0.09
     aportar
    0.08
    Activations Density 0.077%

    No Known Activations