© 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. 11-RESID-POST-AA
    11. 24932
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assimil
    -0.08
     aforementioned
    -0.08
    Ster
    -0.08
    lla
    -0.08
    inidad
    -0.08
    ühr
    -0.08
     revolutionary
    -0.08
    割
    -0.07
    应
    -0.07
    uhur
    -0.07
    POSITIVE LOGITS
     Toolkit
    0.08
    (bind
    0.08
    Transient
    0.07
    ighbor
    0.07
     Toggle
    0.07
     =============================================================================
    0.07
     #-}↵
    0.07
    ıyorum
    0.07
    plib
    0.07
     transient
    0.07
    Activations Density 0.010%

    No Known Activations