© 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. 75596
    Prev
    Next
    INDEX
    Explanations

    名

    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
    gle
    -0.08
    ceso
    -0.07
     leichter
    -0.07
    _http
    -0.07
     assim
    -0.07
    Implicit
    -0.07
     resale
    -0.07
     HTTP
    -0.07
     още
    -0.07
    _HTTP
    -0.07
    POSITIVE LOGITS
     freut
    0.08
    :selected
    0.08
     τι
    0.08
     मी
    0.07
     Vernon
    0.07
    arme
    0.07
     Tottenham
    0.07
     Alexander
    0.07
     Mea
    0.07
     praises
    0.07
    Activations Density 0.000%

    No Known Activations