© 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. 24658
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    amiseks
    -0.09
    在那里
    -0.08
     courthouse
    -0.08
     murder
    -0.08
     Milford
    -0.08
     Breast
    -0.08
    ൊരു
    -0.08
     Versa
    -0.08
     triturador
    -0.08
     genügend
    -0.07
    POSITIVE LOGITS
    -cultural
    0.11
     والاج
    0.08
    -economic
    0.08
     âmbito
    0.08
     reput
    0.08
     lingu
    0.08
     maupun
    0.08
     epistem
    0.08
    ,time
    0.07
     dhin
    0.07
    Activations Density 0.109%

    No Known Activations