© 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. 103486
    Prev
    Next
    INDEX
    Explanations

    �

    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
     grote
    -0.08
     both
    -0.08
     individually
    -0.08
    -स
    -0.07
     Individ
    -0.07
     großen
    -0.07
     אתם
    -0.07
     nombreux
    -0.07
     दोनों
    -0.07
     baseline
    -0.07
    POSITIVE LOGITS
    иден
    0.09
    эш
    0.08
    рист
    0.08
    истан
    0.08
    юм
    0.08
    риот
    0.08
    িস্থিত
    0.08
    beratung
    0.08
     ситуации
    0.08
    Nx
    0.08
    Activations Density 0.005%

    No Known Activations