© 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. 26378
    Prev
    Next
    INDEX
    Explanations

    elections and splitting votes

    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
     contrast
    -0.08
     intime
    -0.07
     metaph
    -0.07
     unlike
    -0.07
    frame
    -0.07
    ige
    -0.07
     intimate
    -0.07
    /functions
    -0.07
    بر
    -0.07
     mejor
    -0.07
    POSITIVE LOGITS
     disruptive
    0.10
     disrupting
    0.10
     troisième
    0.09
     तीस
    0.09
     coalition
    0.09
    tributions
    0.09
     disrupt
    0.09
     spoiler
    0.09
     entrants
    0.09
    第三
    0.08
    Activations Density 0.027%

    No Known Activations