© 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. 11-RESID-POST-AA
    11. 91310
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    .props
    -0.10
    _props
    -0.09
     butt
    -0.08
    props
    -0.08
    yo
    -0.08
     ટ્વ
    -0.07
    Props
    -0.07
     motorcycles
    -0.07
    	props
    -0.07
     filmer
    -0.07
    POSITIVE LOGITS
    OEM
    0.08
    _EXTRA
    0.08
     Wirtschaft
    0.07
     Sér
    0.07
    ATL
    0.07
     Derrick
    0.07
     разум
    0.07
    ORDER
    0.07
     Merkur
    0.07
     വര
    0.07
    Activations Density 0.003%

    No Known Activations