© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26408
    Prev
    Next
    INDEX
    Explanations

    Nonsense sentences

    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
    onsa
    -0.08
     toko
    -0.08
    在線
    -0.07
     {?>↵
    -0.07
     φό
    -0.07
    出租
    -0.07
    /Common
    -0.07
     lender
    -0.07
     battery
    -0.07
    Fetcher
    -0.07
    POSITIVE LOGITS
     bizarre
    0.11
     meaningless
    0.10
     weird
    0.09
     whims
    0.09
     strangely
    0.09
     poetic
    0.09
     nonsense
    0.09
    ව්
    0.09
     crypt
    0.09
     nihil
    0.09
    Activations Density 0.403%

    No Known Activations