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. 43444
    Prev
    Next
    INDEX
    Explanations

    mood

    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
    onner
    -0.08
    recipes
    -0.08
     sort
    -0.07
     absorber
    -0.07
     Brits
    -0.07
    Notation
    -0.07
     Hz
    -0.07
    biotic
    -0.07
     underwear
    -0.07
    Hz
    -0.07
    POSITIVE LOGITS
     adalah
    0.10
    则
    0.09
    就是
    0.09
     происходит
    0.09
    คือ
    0.09
    虽然
    0.08
     হচ্ছে
    0.08
    是一
    0.08
     म्हणजे
    0.08
     isə
    0.08
    Activations Density 0.003%

    No Known Activations