© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 19805
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    (){
    ↵
    ↵
    -0.09
    'L
    -0.09
    {x
    -0.08
    hara
    -0.08
    %)↵
    -0.08
    eken
    -0.08
    яжении
    -0.08
    alsch
    -0.08
    %;
    ↵
    -0.08
    )L
    -0.08
    POSITIVE LOGITS
     with
    0.10
     //
    0.09
     several
    0.09
     of
    0.09
     others
    0.09
     
    0.09
    s
    0.08
     various
    0.08
     in
    0.08
      
    0.08
    Activations Density 0.030%

    No Known Activations