© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51061
    Prev
    Next
    INDEX
    Explanations

    words about meaning

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouze
    -0.10
     শুধু
    -0.10
     només
    -0.10
     nikan
    -0.09
     csak
    -0.09
    ikuti
    -0.09
     শুধ
    -0.08
     chete
    -0.08
     celle
    -0.08
     sadece
    -0.08
    POSITIVE LOGITS
     betekenen
    0.20
     قوله
    0.19
     entail
    0.18
     entails
    0.18
     accomplish
    0.17
     doing
    0.17
     significa
    0.17
     значит
    0.15
     dizer
    0.15
     accomplishing
    0.15
    Activations Density 0.089%

    No Known Activations