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. 104062
    Prev
    Next
    INDEX
    Explanations

    solving math problems

    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
    urados
    -0.09
      
    -0.08
    Anyone
    -0.08
    本网
    -0.08
    ifetime
    -0.08
    Our
    -0.08
    Done
    -0.07
    itamos
    -0.07
    ewn
    -0.07
    erseys
    -0.07
    POSITIVE LOGITS
     먼저
    0.08
     rozw
    0.08
     zunächst
    0.08
     imam
    0.08
     royale
    0.08
    .subtract
    0.07
     reš
    0.07
     auditions
    0.07
     lal
    0.07
     substitute
    0.07
    Activations Density 0.049%

    No Known Activations