© 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. 54628
    Prev
    Next
    INDEX
    Explanations

    similes and comparisons

    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
     jumping
    -0.10
     jump
    -0.10
    jump
    -0.09
     jumps
    -0.09
     jumped
    -0.09
     확보
    -0.09
     leaps
    -0.09
     Jump
    -0.08
     bold
    -0.08
     outrageous
    -0.08
    POSITIVE LOGITS
     gentle
    0.18
     soothing
    0.16
    柔
    0.16
     softly
    0.15
     gently
    0.15
     suaves
    0.15
     serene
    0.15
     doucement
    0.14
     мяг
    0.14
     Gentle
    0.14
    Activations Density 0.179%

    No Known Activations