© 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. 68395
    Prev
    Next
    INDEX
    Explanations

    aggregate

    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
     viviendo
    -0.08
     signature
    -0.08
     હતો
    -0.08
    signature
    -0.08
    OLUME
    -0.08
    iously
    -0.08
     residence
    -0.08
     السف
    -0.08
    ător
    -0.08
     wach
    -0.08
    POSITIVE LOGITS
     aggregated
    0.11
     aggregate
    0.11
     anonym
    0.10
     Aggregate
    0.10
    Aggreg
    0.10
    aggregate
    0.10
    aggreg
    0.10
     gesammelt
    0.10
     summaries
    0.10
    .aggregate
    0.10
    Activations Density 0.007%

    No Known Activations