© 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. 65329
    Prev
    Next
    INDEX
    Explanations

    recording

    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
     internships
    -0.08
     confort
    -0.08
    oys
    -0.08
     kolon
    -0.07
     collectiv
    -0.07
    ,sum
    -0.07
     коллектив
    -0.07
    exclusive
    -0.07
    =sum
    -0.07
     unrealistic
    -0.07
    POSITIVE LOGITS
     publishes
    0.09
     публика
    0.09
     julka
    0.09
     publier
    0.08
     published
    0.08
     veröff
    0.08
     permalink
    0.08
     публи
    0.08
     게시
    0.08
     permanence
    0.08
    Activations Density 0.008%

    No Known Activations