© 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. 75444
    Prev
    Next
    INDEX
    Explanations

    business processes and challenges

    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
     :)↵
    -0.07
    .loc
    -0.07
    yii
    -0.07
     Morris
    -0.07
     violin
    -0.07
    :::
    -0.07
     Vertreter
    -0.07
    Worksheet
    -0.07
     aventures
    -0.07
     Example
    -0.07
    POSITIVE LOGITS
    ，需要
    0.10
     слишком
    0.09
     frag
    0.09
     demasi
    0.09
     sheer
    0.09
    umbersome
    0.09
     bureaucracy
    0.09
    лишком
    0.09
     scalability
    0.09
    ciąż
    0.09
    Activations Density 0.095%

    No Known Activations