© 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. 99157
    Prev
    Next
    INDEX
    Explanations

    diagram label inconsistencies

    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
     pors
    -0.08
    çok
    -0.08
     aur
    -0.07
    iai
    -0.07
     TEC
    -0.07
     zuh
    -0.07
     amit
    -0.07
     получится
    -0.07
     TVA
    -0.07
     Zhao
    -0.07
    POSITIVE LOGITS
    注明
    0.11
     표시
    0.10
     ozn
    0.09
     misleading
    0.09
     indicates
    0.08
     стрел
    0.08
     caption
    0.08
    ుమ
    0.08
     labeling
    0.08
     indicate
    0.08
    Activations Density 0.009%

    No Known Activations