Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97149
    Prev
    Next
    INDEX
    Explanations

    embroidery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decorated
    -0.11
     reconstructed
    -0.10
     prerecorded
    -0.09
    Decor
    -0.09
    decor
    -0.09
     statue
    -0.09
    rafted
    -0.09
    styled
    -0.09
    _OBJECT
    -0.08
     reconstruct
    -0.08
    POSITIVE LOGITS
     embroidery
    0.11
     mon
    0.11
     trimming
    0.10
    _thread
    0.10
     zari
    0.10
     thread
    0.10
     trim
    0.09
     et
    0.09
     embro
    0.09
     trims
    0.09
    Activations Density 0.013%

    No Known Activations