© 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. 16315
    Prev
    Next
    INDEX
    Explanations

    are

    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
     oluline
    -0.11
     weyn
    -0.08
     DCHECK
    -0.08
     Tako
    -0.08
    øy
    -0.08
     tärke
    -0.08
     Lorraine
    -0.08
    uyen
    -0.08
     habido
    -0.08
    Jetzt
    -0.08
    POSITIVE LOGITS
     birbir
    0.13
     collectively
    0.12
     themselves
    0.12
    :↵↵
    0.12
     arasında
    0.12
     आहेत
    0.11
     arranged
    0.11
    :
    0.11
     арасында
    0.11
     തമ്മ
    0.11
    Activations Density 0.075%

    No Known Activations