© 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. 65397
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     اهم
    -0.08
     middelen
    -0.08
     ряда
    -0.08
     فرهنگی
    -0.08
    Չ
    -0.08
     دستی
    -0.08
     делу
    -0.08
    Paperback
    -0.08
    Clinic
    -0.08
     Bonjour
    -0.08
    POSITIVE LOGITS
    -info
    0.08
    hair
    0.08
     hair
    0.08
     info
    0.08
     pregnant
    0.08
     hunter
    0.07
     wanna
    0.07
    female
    0.07
     vertices
    0.07
     depiction
    0.07
    Activations Density 0.004%

    No Known Activations