© 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. 94823
    Prev
    Next
    INDEX
    Explanations

    institution

    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
    ewel
    -0.08
    annin
    -0.08
     mwingine
    -0.08
    ijek
    -0.08
    aliwa
    -0.07
     Kleine
    -0.07
     mobilisation
    -0.07
     Verbrauch
    -0.07
     Gravel
    -0.07
    ọrun
    -0.07
    POSITIVE LOGITS
    所属
    0.12
    職
    0.10
    勤務
    0.10
    Institution
    0.10
     affiliation
    0.09
     affiliated
    0.09
    职位
    0.09
     affiliations
    0.09
    Sponsored
    0.09
    Department
    0.08
    Activations Density 0.162%

    No Known Activations