© 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. 11-RESID-POST-AA
    11. 65554
    Prev
    Next
    INDEX
    Explanations

    literary analysis excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Downloads
    -0.09
     пайдал
    -0.08
    _DOWNLOAD
    -0.08
     category
    -0.08
     доход
    -0.08
     selenium
    -0.08
     download
    -0.08
     amas
    -0.08
     downloads
    -0.08
     Dankzij
    -0.08
    POSITIVE LOGITS
     metaphor
    0.13
    描
    0.12
     poetic
    0.11
     whimsical
    0.11
     nostalgic
    0.10
     imagery
    0.10
     evoc
    0.10
     suggests
    0.10
     nostalg
    0.10
     sarcast
    0.10
    Activations Density 0.051%

    No Known Activations