© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8091
    Prev
    Next
    INDEX
    Explanations

    fountain

    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
     loj
    -0.09
     Sutton
    -0.08
    lasht
    -0.08
     impending
    -0.07
    cznych
    -0.07
     creditors
    -0.07
     isolation
    -0.07
     sombre
    -0.07
     Orth
    -0.07
    ザー
    -0.07
    POSITIVE LOGITS
     fountains
    0.09
     GAP
    0.09
    anlagen
    0.09
     multifunction
    0.08
     ಬೀ
    0.08
    喷水
    0.08
    иться
    0.08
     Vivian
    0.08
     malfunction
    0.08
     faucets
    0.08
    Activations Density 0.004%

    No Known Activations