© 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. 19-RESID-POST-AA
    11. 103226
    Prev
    Next
    INDEX
    Explanations

    array data structures

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    「
    -0.11
    “
    -0.11
    、「
    -0.10
    «
    -0.10
     “
    -0.10
    ("
    -0.09
    「あ
    -0.09
     „
    -0.09
     "
    -0.09
    ”
    -0.09
    POSITIVE LOGITS
     array
    0.09
    ्ली
    0.08
     IRS
    0.08
    анов
    0.08
    (array
    0.07
    .array
    0.07
    ,array
    0.07
     arrays
    0.07
     absolute
    0.07
     commonly
    0.07
    Activations Density 0.000%

    No Known Activations