© 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. 95864
    Prev
    Next
    INDEX
    Explanations

    accretion

    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
    Life
    -0.09
    life
    -0.08
     sitcom
    -0.08
     الحياة
    -0.08
    cela
    -0.07
    ירת
    -0.07
     الفصل
    -0.07
    spring
    -0.07
    春
    -0.07
    Save
    -0.07
    POSITIVE LOGITS
     mergers
    0.13
     accumulation
    0.12
     merging
    0.11
     aggregation
    0.11
     वृद्धि
    0.10
     assimilation
    0.10
     absorption
    0.10
     merges
    0.10
     uptake
    0.10
     +=
    0.10
    Activations Density 0.007%

    No Known Activations