© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99326
    Prev
    Next
    INDEX
    Explanations

    digit sum 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
    人才
    -0.08
     Euch
    -0.08
     menik
    -0.08
     Pets
    -0.08
     Eup
    -0.07
    μου
    -0.07
     Interested
    -0.07
    民族
    -0.07
    客户端下载
    -0.07
    ,此
    -0.07
    POSITIVE LOGITS
    Sum
    0.10
     sum
    0.09
     Sum
    0.09
     сумма
    0.09
     sums
    0.08
    xffff
    0.08
    _sum
    0.08
     somme
    0.08
     batterij
    0.08
     суммы
    0.08
    Activations Density 0.024%

    No Known Activations