© 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. 7-RESID-POST-AA
    11. 1508
    Prev
    Next
    INDEX
    Explanations

    recycle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lp
    -0.08
     proc
    -0.08
     propriet
    -0.08
    -0.08
     congr
    -0.08
     càng
    -0.08
    bouwen
    -0.07
    产权
    -0.07
     impr
    -0.07
     corresponde
    -0.07
    POSITIVE LOGITS
     Deleted
    0.12
     Removed
    0.10
     нен
    0.09
     geraakt
    0.08
     Naughty
    0.08
     Tempor
    0.08
     verwijderd
    0.08
     Ala
    0.08
     keessaa
    0.08
     Avoid
    0.08
    Activations Density 0.004%
    No Known Activations