Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120359
    Prev
    Next
    INDEX
    Explanations

    differential diagnosis

    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
     descobrir
    -0.08
     consisted
    -0.08
    .");
    -0.08
     Intel
    -0.07
     encontro
    -0.07
     indik
    -0.07
     motto
    -0.07
     encontró
    -0.07
     });
    -0.07
     plong
    -0.07
    POSITIVE LOGITS
     competing
    0.10
     endemic
    0.08
     ఇతర
    0.08
    obu
    0.08
     confuse
    0.08
     compete
    0.08
     miiran
    0.08
     confund
    0.08
     cellul
    0.08
    ére
    0.07
    Activations Density 0.013%

    No Known Activations