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. 78747
    Prev
    Next
    INDEX
    Explanations

    filter

    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
     mith
    -0.08
    จ
    -0.07
     sfeer
    -0.07
     stopper
    -0.07
     stopped
    -0.07
    Ø
    -0.07
     vibe
    -0.07
     redund
    -0.07
    Management
    -0.07
     staged
    -0.07
    POSITIVE LOGITS
     truths
    0.08
     ಪ್ರ
    0.07
     שזה
    0.07
     खुशी
    0.07
    icionar
    0.07
    верд
    0.07
     бағдар
    0.07
     oneself
    0.07
     하
    0.07
    _cpp
    0.07
    Activations Density 0.004%

    No Known Activations