© 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. 94985
    Prev
    Next
    INDEX
    Explanations

    gimbal lock

    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
    Tá
    -0.08
    irmək
    -0.08
     coping
    -0.08
    avanja
    -0.08
    واک
    -0.08
    ীক
    -0.07
     neamh
    -0.07
    Ê
    -0.07
    ína
    -0.07
    Variables
    -0.07
    POSITIVE LOGITS
     Lotus
    0.08
     Depot
    0.07
     персона
    0.07
     Stor
    0.07
     Comedy
    0.07
     Cherry
    0.07
     Beauty
    0.07
     стро
    0.07
    .Middle
    0.07
    allig
    0.07
    Activations Density 0.001%

    No Known Activations