© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44699
    Prev
    Next
    INDEX
    Explanations

    watch specifications/reviews

    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
     Spawn
    -0.08
    heer
    -0.07
    Degrees
    -0.07
    Spawn
    -0.07
     degrees
    -0.07
    yond
    -0.07
     돈
    -0.07
    onom
    -0.07
     Honors
    -0.07
     आर्थिक
    -0.07
    POSITIVE LOGITS
     bracelet
    0.10
     достав
    0.10
     المعدنية
    0.09
     sapphire
    0.09
     sunscreen
    0.09
     smartwatch
    0.09
     Viking
    0.09
    той
    0.09
     Bracelet
    0.08
    ват
    0.08
    Activations Density 0.007%

    No Known Activations