© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113681
    Prev
    Next
    INDEX
    Explanations

    escalators

    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
    章节
    -0.09
     अध्य
    -0.08
     chapter
    -0.08
     capítulos
    -0.08
     סדר
    -0.08
     sect
    -0.08
     REC
    -0.08
     duelo
    -0.08
     chapters
    -0.07
     dbo
    -0.07
    POSITIVE LOGITS
     conveyor
    0.13
     Conveyor
    0.11
     conveyors
    0.10
    ww
    0.08
     beds
    0.08
     mechanically
    0.08
     scrolling
    0.08
     Playback
    0.08
     chim
    0.08
     locom
    0.08
    Activations Density 0.005%

    No Known Activations