© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 49339
    Prev
    Next
    INDEX
    Explanations

    local

    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
    	Global
    -0.12
     Global
    -0.12
     글로벌
    -0.11
     全球
    -0.10
    	global
    -0.10
     Worldwide
    -0.10
     globals
    -0.10
     Globals
    -0.10
    _Global
    -0.09
     Первый
    -0.09
    POSITIVE LOGITS
     extrem
    0.15
     extrema
    0.14
    Ext
    0.13
    _ext
    0.13
     optimum
    0.12
     extreem
    0.12
     maximum
    0.12
     minimum
    0.12
     behavior
    0.11
     экст
    0.11
    Activations Density 0.009%

    No Known Activations