© 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. 7552
    Prev
    Next
    INDEX
    Explanations

    distinct sets/math problems

    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
     fürs
    -0.08
     grat
    -0.08
     για
    -0.07
    ρει
    -0.07
    ümüzde
    -0.07
     "))
    -0.07
    ½
    -0.07
     impatient
    -0.07
     construido
    -0.07
     patience
    -0.07
    POSITIVE LOGITS
    Distinct
    0.10
    -separated
    0.10
     overlapping
    0.10
    Separ
    0.10
     distinctly
    0.10
    Overlap
    0.10
     separation
    0.10
     distinct
    0.10
     Exclus
    0.10
     overlaps
    0.10
    Activations Density 0.038%

    No Known Activations