© 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 EvalsExportsAPI 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. 19855
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     masih
    -0.09
     యొక్క
    -0.08
     ogé
    -0.08
     líka
    -0.08
     的
    -0.08
     નું
    -0.08
     nochmals
    -0.08
    quires
    -0.08
     aún
    -0.08
     এখনও
    -0.08
    POSITIVE LOGITS
    จาก
    0.11
    ેથી
    0.11
    -to
    0.10
     থেকেই
    0.10
    كتب
    0.10
    ๆ
    0.10
    々
    0.09
    然
    0.09
    arily
    0.09
    -stage
    0.09
    Activations Density 0.003%

    No Known Activations