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. 106095
    Prev
    Next
    INDEX
    Explanations

    minimum of functions

    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
    .TABLE
    -0.09
     الزيت
    -0.08
     steril
    -0.08
     علماء
    -0.08
    -et
    -0.08
     biomass
    -0.08
     autograph
    -0.08
     Algem
    -0.08
     Steam
    -0.08
     flagship
    -0.08
    POSITIVE LOGITS
     symmetrical
    0.08
     centered
    0.08
     valley
    0.08
     peaks
    0.08
     convex
    0.08
     freeway
    0.08
     valleys
    0.08
     minima
    0.08
     palindrome
    0.08
     peak
    0.08
    Activations Density 0.051%

    No Known Activations