© 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. 19-RESID-POST-AA
    11. 103312
    Prev
    Next
    INDEX
    Explanations

    parent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allies
    -0.09
     stimuleren
    -0.08
    -0.08
    IVITY
    -0.08
     собственного
    -0.07
     преиму
    -0.07
     собственной
    -0.07
     преимуществ
    -0.07
    Bookmark
    -0.07
    _BGR
    -0.07
    POSITIVE LOGITS
     interactions
    0.11
    会议
    0.11
    关系
    0.11
    沟
    0.11
    -company
    0.10
     ബന്ധ
    0.10
     ವಿಚಾರ
    0.10
     interaction
    0.10
     ಪ್ರಶ್ನ
    0.10
    -manager
    0.10
    Activations Density 0.005%
    No Known Activations