© 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. 7-RESID-POST-AA
    11. 1329
    Prev
    Next
    INDEX
    Explanations

    surge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     COPYRIGHT
    -0.09
     ós
    -0.09
     plag
    -0.09
    esson
    -0.08
    uppen
    -0.08
     libs
    -0.08
    jahr
    -0.08
    .COMP
    -0.08
    Artifacts
    -0.08
     coherent
    -0.08
    POSITIVE LOGITS
    Taxi
    0.12
     Taxi
    0.12
     Uber
    0.12
     taxis
    0.11
     taxi
    0.11
    司机
    0.11
    Uber
    0.10
    配送
    0.10
     chauffeur
    0.10
     Lyft
    0.10
    Activations Density 0.039%

    No Known Activations