© 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. 49017
    Prev
    Next
    INDEX
    Explanations

    Rocks and minerals

    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
     desn
    -0.10
     {|
    -0.08
    -0.08
    .Meta
    -0.08
    841
    -0.08
     ระบบ
    -0.07
     ศ
    -0.07
     escult
    -0.07
    Veget
    -0.07
     பால
    -0.07
    POSITIVE LOGITS
    ersut
    0.18
     яш
    0.09
    ydym
    0.09
     app
    0.09
    azit
    0.08
    klary
    0.08
    uvian
    0.08
    irite
    0.08
    avent
    0.08
     allan
    0.08
    Activations Density 0.004%

    No Known Activations