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. 12267
    Prev
    Next
    INDEX
    Explanations

    What

    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
    исты
    -0.08
    edded
    -0.08
    eddings
    -0.08
     فى
    -0.08
    aging
    -0.07
     boul
    -0.07
    шийся
    -0.07
     அத
    -0.07
     coax
    -0.07
     сюда
    -0.07
    POSITIVE LOGITS
     analytics
    0.08
    👉
    0.08
    ì
    0.07
     �
    0.07
     زی
    0.07
     sanit
    0.07
     runners
    0.07
     Sanit
    0.07
    �
    0.07
    _need
    0.07
    Activations Density 0.018%

    No Known Activations