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. 111472
    Prev
    Next
    INDEX
    Explanations

    child

    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
    短信
    -0.08
    .mn
    -0.07
     Quand
    -0.07
     cik
    -0.07
    _SMS
    -0.07
     distributed
    -0.07
     quadru
    -0.07
     Kigali
    -0.07
     qualcosa
    -0.07
    ಸ್ತಿ
    -0.07
    POSITIVE LOGITS
    에게
    0.10
    喜欢
    0.09
    -anak
    0.09
    ңыз
    0.08
     accustomed
    0.08
    喜
    0.08
    们
    0.08
    rens
    0.08
    :inline
    0.08
    Reaction
    0.08
    Activations Density 0.050%

    No Known Activations