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. 23-RESID-POST-AA
    6. 131067
    Prev
    Next
    INDEX
    Explanations

    say 20

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ிள
    -0.10
     ezig
    -0.10
    ells
    -0.09
    255
    -0.09
     $\
    -0.09
     phi
    -0.09
     dots
    -0.09
    xff
    -0.09
    ξύ
    -0.09
    psi
    -0.09
    POSITIVE LOGITS
    20
    0.17
    ২০
    0.15
    २०
    0.13
     veinte
    0.12
     двад
    0.12
    ۲۰
    0.12
    20
    0.12
     twenty
    0.11
    ૨૦
    0.10
     twintig
    0.10
    Activations Density 0.111%

    No Known Activations