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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 186
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wraz
    -0.09
     quake
    -0.08
    antar
    -0.08
    liter
    -0.08
     electrón
    -0.08
    nader
    -0.08
     antaŭ
    -0.08
    pipes
    -0.07
     παρέ
    -0.07
     razem
    -0.07
    POSITIVE LOGITS
    uffy
    0.09
     cinematic
    0.09
     glamour
    0.08
     glam
    0.08
     সিনেম
    0.08
     midi
    0.08
    露脸
    0.08
     dramatically
    0.08
     चम
    0.08
     muc
    0.08
    Activations Density 0.000%

    No Known Activations