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. 119376
    Prev
    Next
    INDEX
    Explanations

    rather

    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
     terrible
    -0.09
     prefixes
    -0.09
     Rutherford
    -0.08
     IZ
    -0.08
     curls
    -0.08
     sucks
    -0.08
    лова
    -0.08
     voorkomen
    -0.07
     יהיו
    -0.07
     saab
    -0.07
    POSITIVE LOGITS
     ọma
    0.08
    कर
    0.08
     accurately
    0.08
     competency
    0.07
    Whats
    0.07
     الصحيح
    0.07
     swiftly
    0.07
     đầy
    0.07
    അത
    0.07
    ความ
    0.07
    Activations Density 0.542%

    No Known Activations