© 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. 47366
    Prev
    Next
    INDEX
    Explanations

    questions and how to

    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
     possession
    -0.08
    _MODE
    -0.08
     lost
    -0.08
    قديم
    -0.08
    _CALL
    -0.08
    _RUNNING
    -0.07
    bin
    -0.07
    abilité
    -0.07
    Mode
    -0.07
    MODE
    -0.07
    POSITIVE LOGITS
    促进
    0.14
    ಿಸುತ್ತದೆ
    0.13
     способствует
    0.12
     باعث
    0.12
     позволяют
    0.12
    ирует
    0.12
     تؤ
    0.11
     обеспечивает
    0.11
     કરે
    0.11
     sağlar
    0.11
    Activations Density 0.254%

    No Known Activations