© 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. 23-RESID-POST-AA
    11. 47543
    Prev
    Next
    INDEX
    Explanations

    Marketing, bidding, and budgeting

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acute
    -0.09
     unmittelbar
    -0.09
     immédiatement
    -0.09
     qualific
    -0.08
     Hang
    -0.08
     sanitation
    -0.08
     sanad
    -0.08
    注销
    -0.08
     materiał
    -0.08
    acute
    -0.08
    POSITIVE LOGITS
    Enhanced
    0.10
     став
    0.10
     Enhanced
    0.09
    Max
    0.09
     ставка
    0.09
    Percentage
    0.09
    Shared
    0.08
     максим
    0.08
     процент
    0.08
    Curve
    0.08
    Activations Density 0.002%

    No Known Activations