© 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. 19-RESID-POST-AA
    11. 102790
    Prev
    Next
    INDEX
    Explanations

    intersect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ورود
    -0.09
     সাথে
    -0.09
     interactions
    -0.09
    Interactions
    -0.09
    กับ
    -0.08
     với
    -0.08
    ೊಂದಿಗೆ
    -0.08
     entrances
    -0.08
    與
    -0.08
     with
    -0.08
    POSITIVE LOGITS
     somewhere
    0.12
     someplace
    0.12
     point
    0.11
    _point
    0.11
    一点
    0.11
    ing
    0.11
     പോയ
    0.10
    ed
    0.10
    Point
    0.10
    -point
    0.10
    Activations Density 0.006%

    No Known Activations