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. 120209
    Prev
    Next
    INDEX
    Explanations

    common factor

    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
     Recover
    -0.08
    av
    -0.07
     Candidate
    -0.07
    	attr
    -0.07
     repro
    -0.07
    alami
    -0.07
      ↵↵  ↵↵
    -0.07
    unik
    -0.07
     degrad
    -0.07
              
    -0.07
    POSITIVE LOGITS
     хим
    0.08
    appropr
    0.08
    idges
    0.08
     tercih
    0.08
    即可
    0.08
    дегі
    0.07
    Voltage
    0.07
     anton
    0.07
     Myth
    0.07
     অধ্য
    0.07
    Activations Density 0.029%

    No Known Activations