© 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. 96453
    Prev
    Next
    INDEX
    Explanations

    Unknown token

    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
     forg
    -0.08
     let
    -0.08
     dị
    -0.07
    ાફ
    -0.07
    	let
    -0.07
     ban
    -0.07
    飛
    -0.07
     FF
    -0.07
     футб
    -0.07
     alk
    -0.07
    POSITIVE LOGITS
    �
    0.10
    ุบ
    0.08
     '__
    0.08
     mineria
    0.08
    _SLOT
    0.08
    식
    0.08
     %{
    0.08
    051
    0.07
     Evol
    0.07
    072
    0.07
    Activations Density 0.001%

    No Known Activations