© 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. 99271
    Prev
    Next
    INDEX
    Explanations

    m

    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
     matrícula
    -0.08
     absorbs
    -0.08
     considering
    -0.08
    ichtung
    -0.07
    考虑
    -0.07
    /graphql
    -0.07
     બાદ
    -0.07
     enclosure
    -0.07
     mempert
    -0.07
    规
    -0.07
    POSITIVE LOGITS
     Dam
    0.08
    vić
    0.08
     ambul
    0.08
    -ms
    0.08
    -files
    0.08
     カ
    0.08
    @Required
    0.08
     Kay
    0.07
     aure
    0.07
     cupid
    0.07
    Activations Density 0.001%

    No Known Activations