Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 501
    Prev
    Next
    INDEX
    Explanations

    Ruby

    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
     demandas
    -0.08
     worlds
    -0.08
    annar
    -0.08
     technologically
    -0.08
     catalogs
    -0.07
    与此同时
    -0.07
     catálogo
    -0.07
     tanta
    -0.07
     Ah
    -0.07
     Gartner
    -0.07
    POSITIVE LOGITS
    exe
    0.08
     mail
    0.08
    memo
    0.07
    -də
    0.07
     prowess
    0.07
    _stmt
    0.07
     작성
    0.07
     وچ
    0.07
     中
    0.07
    Mail
    0.07
    Activations Density 0.012%

    No Known Activations