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. 103265
    Prev
    Next
    INDEX
    Explanations

    custom

    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
     insta
    -0.08
    夏
    -0.07
    服
    -0.07
     người
    -0.07
     toc
    -0.07
     Corpus
    -0.07
     Flynn
    -0.07
    üc
    -0.07
    liter
    -0.07
    ermi
    -0.07
    POSITIVE LOGITS
    -made
    0.10
     biệt
    0.10
    isable
    0.09
    izable
    0.09
    izations
    0.09
    /custom
    0.08
     Legion
    0.08
    Owned
    0.08
    (Const
    0.07
    édit
    0.07
    Activations Density 0.014%

    No Known Activations