© 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. 102151
    Prev
    Next
    INDEX
    Explanations

    reputation

    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
    歌词
    -0.09
     lyrics
    -0.09
     interpretación
    -0.08
     karar
    -0.08
     تفسير
    -0.08
     класси
    -0.08
     متن
    -0.07
    Notation
    -0.07
     ancestry
    -0.07
     halluc
    -0.07
    POSITIVE LOGITS
     opgebouwd
    0.14
     garnered
    0.12
     construída
    0.11
     bât
    0.11
     구축
    0.11
     상승
    0.11
    worthiness
    0.11
     perante
    0.10
    築
    0.10
     laundering
    0.10
    Activations Density 0.030%

    No Known Activations