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. 56244
    Prev
    Next
    INDEX
    Explanations

    code/equations

    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
     Moore
    -0.07
     préalable
    -0.07
    た
    -0.07
     знаний
    -0.07
    ത്തോടെ
    -0.07
     Nicholson
    -0.07
     निर्ण
    -0.07
    Seller
    -0.07
    kong
    -0.07
    ngr
    -0.07
    POSITIVE LOGITS
    চ
    0.08
     dumps
    0.08
     unchanged
    0.07
     //"
    0.07
     owo
    0.07
     interrupted
    0.07
    .Amount
    0.07
     перечис
    0.07
                                                                                                                                    
    0.07
      
    0.07
    Activations Density 0.009%

    No Known Activations