© 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. 44796
    Prev
    Next
    INDEX
    Explanations

    review over

    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
    ंब
    -0.08
     tmp
    -0.08
    ément
    -0.07
     развитие
    -0.07
    甘
    -0.07
     sementara
    -0.07
    ächst
    -0.07
    tmp
    -0.07
     nennen
    -0.07
    ursing
    -0.07
    POSITIVE LOGITS
    资料
    0.10
    Review
    0.10
     Literatura
    0.09
     समीक्षा
    0.09
    -review
    0.09
     literatura
    0.09
     deten
    0.09
    阅
    0.09
     NSDictionary
    0.09
     revisar
    0.09
    Activations Density 0.041%

    No Known Activations