© 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. 29649
    Prev
    Next
    INDEX
    Explanations

    quantity word problems

    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
    850
    -0.09
     দক্ষিণ
    -0.08
    812
    -0.08
    )?;↵↵
    -0.08
     Sask
    -0.07
    ವಾ
    -0.07
     Barrio
    -0.07
     Fang
    -0.07
    akathi
    -0.07
    avlj
    -0.07
    POSITIVE LOGITS
     चाहे
    0.08
    Anything
    0.08
     sexy
    0.07
    -care
    0.07
     будь
    0.07
     thưởng
    0.07
     CME
    0.07
    시면
    0.07
     réuss
    0.07
     réussi
    0.07
    Activations Density 0.033%

    No Known Activations