© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 853
    Prev
    Next
    INDEX
    Explanations

    magic spells

    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
     Hyd
    -0.08
     calibre
    -0.08
     surt
    -0.08
     fick
    -0.08
    	html
    -0.07
     issues
    -0.07
    Dom
    -0.07
     소재
    -0.07
     frontend
    -0.07
    _holder
    -0.07
    POSITIVE LOGITS
     bail
    0.08
     ŝ
    0.07
     тіл
    0.07
    ългар
    0.07
     remember
    0.07
     Nazi
    0.07
    BQ
    0.07
    ɗ
    0.07
    _FIXED
    0.07
     продолжа
    0.07
    Activations Density 0.001%

    No Known Activations