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. 15-RESID-POST-AA
    6. 18973
    Prev
    Next
    INDEX
    Explanations

    censor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .datasource
    -0.09
    -0.08
    既
    -0.08
     Point
    -0.07
     National
    -0.07
    .food
    -0.07
    _datas
    -0.07
     contenders
    -0.07
     atual
    -0.07
     Nest
    -0.07
    POSITIVE LOGITS
     punctuation
    0.10
    /el
    0.10
    /self
    0.09
     omissions
    0.09
    edit
    0.08
     gebleven
    0.08
    ="";
    ↵
    0.08
     censor
    0.08
     சொல்ல
    0.08
    unless
    0.08
    Activations Density 0.002%

    No Known Activations