© 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. 129248
    Prev
    Next
    INDEX
    Explanations

    necessary

    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
    ិប
    -0.09
     情
    -0.08
     conflito
    -0.08
     “[
    -0.08
     پرو
    -0.07
     تمكن
    -0.07
     المواد
    -0.07
    یره
    -0.07
     détails
    -0.07
     긴
    -0.07
    POSITIVE LOGITS
     hingegen
    0.08
    akar
    0.08
    .jpg
    0.07
    -less
    0.07
    junto
    0.07
     parcial
    0.07
     Dixon
    0.07
    ɓ
    0.07
    RECT
    0.07
    .chrom
    0.07
    Activations Density 0.004%

    No Known Activations