© 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. 11-RESID-POST-AA
    11. 44613
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     municipality
    -0.08
     municipal
    -0.08
     obe
    -0.07
     billet
    -0.07
    .vue
    -0.07
     infants
    -0.07
    .internal
    -0.07
     indiv
    -0.07
     cute
    -0.07
     пункт
    -0.07
    POSITIVE LOGITS
     ehemal
    0.11
     retired
    0.11
     formerly
    0.11
     ehemaligen
    0.10
    formerly
    0.10
     ehemalige
    0.10
     reminis
    0.10
     resigned
    0.10
     voormal
    0.09
     మాజీ
    0.09
    Activations Density 0.159%

    No Known Activations