© 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. 15-RESID-POST-AA
    11. 16705
    Prev
    Next
    INDEX
    Explanations

    fibonacci

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pí
    -0.08
    Pixel
    -0.07
     Már
    -0.07
    _PIXEL
    -0.07
     immigrant
    -0.07
    חדש
    -0.07
     imported
    -0.07
     afternoon
    -0.07
    擦
    -0.07
     geographical
    -0.07
    POSITIVE LOGITS
     upto
    0.12
    _generation
    0.11
     Generation
    0.11
     fibonacci
    0.11
     generation
    0.11
     покол
    0.10
    generation
    0.10
     생성
    0.10
    .Generation
    0.10
    Generation
    0.10
    Activations Density 0.008%

    No Known Activations