© 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. 23-RESID-POST-AA
    11. 5599
    Prev
    Next
    INDEX
    Explanations

    coefficient

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    credentials
    -0.13
    _coordinates
    -0.13
    coordinates
    -0.13
     Coordinates
    -0.13
     coordinates
    -0.12
     credentials
    -0.12
    Coordinates
    -0.12
     координ
    -0.12
    coords
    -0.12
    .coordinates
    -0.12
    POSITIVE LOGITS
    icients
    0.12
     multiplying
    0.11
     times
    0.11
     c
    0.11
     preceding
    0.10
     term
    0.10
    iciente
    0.10
     앞
    0.09
     before
    0.09
    ally
    0.09
    Activations Density 0.053%

    No Known Activations