© 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. 7-RESID-POST-AA
    11. 1154
    Prev
    Next
    INDEX
    Explanations

    orientation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erzielen
    -0.08
     fract
    -0.08
     philanthropic
    -0.08
     comedic
    -0.08
     Truly
    -0.07
     profits
    -0.07
     Null
    -0.07
     Forbes
    -0.07
     Tomas
    -0.07
     gcd
    -0.07
    POSITIVE LOGITS
     안내
    0.12
     onboarding
    0.12
     accl
    0.11
     स्वागत
    0.11
     സ്വാഗത
    0.11
     bienvenue
    0.11
     Procedures
    0.11
    歓迎
    0.11
     welcoming
    0.11
     acquaint
    0.10
    Activations Density 0.141%

    No Known Activations