© 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. 96657
    Prev
    Next
    INDEX
    Explanations

    Minimization and maximization

    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
     специаль
    -0.08
     spezielle
    -0.08
     måste
    -0.08
    special
    -0.07
     неправиль
    -0.07
     詳
    -0.07
     Must
    -0.07
    必
    -0.07
     Fifth
    -0.07
     repente
    -0.07
    POSITIVE LOGITS
     möglichst
    0.32
     maximize
    0.28
     όσο
    0.27
    尽
    0.27
     minimize
    0.26
     maximizing
    0.24
     minimizes
    0.24
     cât
    0.23
     ideally
    0.22
     minimizing
    0.22
    Activations Density 0.168%

    No Known Activations