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. 61032
    Prev
    Next
    INDEX
    Explanations

    feed-in tariffs policies

    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
     centrum
    -0.09
     Centrum
    -0.08
     مرکز
    -0.08
     الوسط
    -0.08
     hollywood
    -0.08
     suff
    -0.07
    ismen
    -0.07
    sem
    -0.07
    occus
    -0.07
     Suff
    -0.07
    POSITIVE LOGITS
    adó
    0.08
     finder
    0.07
     guaranteed
    0.07
     policy
    0.07
     verpflichtet
    0.07
     Tener
    0.07
     policies
    0.07
    boost
    0.07
     ofrec
    0.07
     kopp
    0.07
    Activations Density 0.004%

    No Known Activations