© 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. 102962
    Prev
    Next
    INDEX
    Explanations

    elif

    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
     使用
    -0.08
     内容
    -0.08
     सामग्री
    -0.08
     　　
    -0.08
    内容
    -0.08
     用
    -0.08
     两
    -0.08
     fortuna
    -0.07
     schade
    -0.07
     TPU
    -0.07
    POSITIVE LOGITS
     elif
    0.11
    agasy
    0.10
    -benar
    0.10
    യായ
    0.09
    -than
    0.09
    ‍රී
    0.09
    மான
    0.09
    වර
    0.09
    మైన
    0.08
     ქართულ
    0.08
    Activations Density 0.000%

    No Known Activations