© 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. 3-RESID-POST-AA
    11. 1293
    Prev
    Next
    INDEX
    Explanations

    pascal keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ening
    -0.10
     ಅವ
    -0.08
     impressão
    -0.08
    DX
    -0.07
     Ezek
    -0.07
     shed
    -0.07
     Reciprocity
    -0.07
     Arrow
    -0.07
     socioeconomic
    -0.07
     निक
    -0.07
    POSITIVE LOGITS
    =obj
    0.10
     Ia
    0.08
    .exe
    0.08
     capa
    0.07
     osp
    0.07
     gand
    0.07
    Ivan
    0.07
     Hungarian
    0.07
     Xml
    0.07
    (xml
    0.07
    Activations Density 0.002%

    No Known Activations