© 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 EvalsExportsinterp-engineNEWAPI 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. 63050
    Prev
    Next
    INDEX
    Explanations

    relative position

    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
     repert
    -0.08
     conj
    -0.08
    ,{
    -0.08
     rutin
    -0.08
     aptitude
    -0.07
    .cre
    -0.07
     contribut
    -0.07
     flavors
    -0.07
    年份
    -0.07
    .{
    -0.07
    POSITIVE LOGITS
     Positioned
    0.11
     Halo
    0.10
    _position
    0.10
     Position
    0.10
    当前位置
    0.09
    	position
    0.09
     halo
    0.09
     위치
    0.09
     Conveyor
    0.09
    .position
    0.09
    Activations Density 0.021%

    No Known Activations