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. 109553
    Prev
    Next
    INDEX
    Explanations

    to

    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
     imported
    -0.09
    गीत
    -0.08
     využ
    -0.08
     importing
    -0.08
    Brit
    -0.08
    kter
    -0.07
     Prog
    -0.07
     looga
    -0.07
     wh
    -0.07
     dato
    -0.07
    POSITIVE LOGITS
     voire
    0.10
     수준
    0.09
    甚至
    0.08
     prestig
    0.08
     一级
    0.08
     മറ്റ്
    0.08
    _FATAL
    0.08
    �
    0.08
     ואף
    0.08
    وجيه
    0.08
    Activations Density 0.031%

    No Known Activations