© 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. 78039
    Prev
    Next
    INDEX
    Explanations

    joint and several liability

    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
     tunes
    -0.08
    UGAR
    -0.08
    Func
    -0.08
     guts
    -0.08
     tune
    -0.08
     spacer
    -0.07
    Name
    -0.07
    AD
    -0.07
    关闭
    -0.07
    Matcher
    -0.07
    POSITIVE LOGITS
     nhau
    0.10
     equally
    0.10
     ownership
    0.09
     gegense
    0.09
    ownership
    0.09
     partagé
    0.09
     gemeins
    0.09
     iguales
    0.09
    ակալ
    0.08
     partes
    0.08
    Activations Density 0.011%

    No Known Activations