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

    Neuronpedia

    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. 102402
    Prev
    Next
    INDEX
    Explanations

    the ending -tion

    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
    ointer
    -0.08
    류
    -0.08
    래
    -0.08
    ive
    -0.07
    ogeneous
    -0.07
    opause
    -0.07
    uffles
    -0.07
     Kind
    -0.07
    ifiques
    -0.07
    icide
    -0.07
    POSITIVE LOGITS
    ment
    0.13
    ेशन
    0.13
    േഷന്
    0.12
    MENT
    0.12
    ציה
    0.12
    이션
    0.11
    ierungs
    0.11
    atsioon
    0.11
    рован
    0.11
    атора
    0.11
    Activations Density 0.024%

    No Known Activations