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. 55450
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
     malheureusement
    -0.08
    ēt
    -0.08
     biasa
    -0.08
     забот
    -0.08
    ült
    -0.08
     nonprofit
    -0.08
     Zh
    -0.07
     fait
    -0.07
    hä
    -0.07
     الط
    -0.07
    POSITIVE LOGITS
    即可
    0.08
    」は
    0.08
    数据显示
    0.08
    apper
    0.08
    は
    0.07
     blir
    0.07
    аван
    0.07
    _HEADER
    0.07
     செயல
    0.07
    日は
    0.07
    Activations Density 0.183%

    No Known Activations