© 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. 15-RESID-POST-AA
    11. 16412
    Prev
    Next
    INDEX
    Explanations

    these

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clara
    -0.07
     Opposition
    -0.07
    ̊
    -0.07
     opposition
    -0.07
    /dialog
    -0.07
     melted
    -0.07
    Lift
    -0.07
     Opin
    -0.07
     authoritarian
    -0.07
     oste
    -0.07
    POSITIVE LOGITS
     وعدم
    0.09
    _none
    0.09
     tentar
    0.09
     existentes
    0.09
     attempted
    0.09
    Existing
    0.09
    -none
    0.08
     Existing
    0.08
    iany
    0.08
    _existing
    0.08
    Activations Density 0.008%

    No Known Activations