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. 11793
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
     greeting
    -0.08
    ukkan
    -0.08
     назв
    -0.07
     Uhr
    -0.07
    hab
    -0.07
     humidity
    -0.07
    aining
    -0.07
     greetings
    -0.07
    oloa
    -0.07
     значение
    -0.07
    POSITIVE LOGITS
     numerator
    0.10
     denominator
    0.10
     Akron
    0.08
     Crimson
    0.08
     scherpe
    0.08
     Astra
    0.08
     "/"
    0.07
     aure
    0.07
     Patent
    0.07
     avantaj
    0.07
    Activations Density 0.010%

    No Known Activations