© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48041
    Prev
    Next
    INDEX
    Explanations

    cl

    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
    腕
    -0.09
     em
    -0.09
    	em
    -0.08
     tribe
    -0.08
     trek
    -0.08
    বে
    -0.08
     이동
    -0.08
     ugbu
    -0.08
     tribal
    -0.08
     tribes
    -0.08
    POSITIVE LOGITS
     coatings
    0.10
    ADDING
    0.10
     gevel
    0.09
    sges
    0.08
    adding
    0.08
     layoffs
    0.08
     openings
    0.08
     verdu
    0.08
     toiture
    0.08
     coating
    0.07
    Activations Density 0.001%

    No Known Activations