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. 65956
    Prev
    Next
    INDEX
    Explanations

    :

    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
    ায
    -0.08
    ateness
    -0.08
     prescription
    -0.07
     pera
    -0.07
    隐
    -0.07
    URLException
    -0.07
     יחס
    -0.07
     hieman
    -0.07
     لديها
    -0.07
    acea
    -0.07
    POSITIVE LOGITS
     nonstop
    0.09
    .clean
    0.08
     kar
    0.08
     Carlo
    0.08
     renforcer
    0.07
     Elementary
    0.07
     préparer
    0.07
     elementary
    0.07
    ulte
    0.07
    \Collection
    0.07
    Activations Density 0.001%

    No Known Activations