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. 102739
    Prev
    Next
    INDEX
    Explanations

    simple

    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
    breed
    -0.10
     Worst
    -0.08
    usin
    -0.08
    pap
    -0.08
    owing
    -0.07
     Blocking
    -0.07
    оин
    -0.07
    -general
    -0.07
    anha
    -0.07
    Skills
    -0.07
    POSITIVE LOGITS
    -minded
    0.12
     minded
    0.11
    mente
    0.11
     pleasures
    0.08
    ‌تر
    0.08
     جدًا
    0.08
    潔
    0.08
     kt
    0.08
     kokoa
    0.08
     volontaire
    0.08
    Activations Density 0.048%

    No Known Activations