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. 98624
    Prev
    Next
    INDEX
    Explanations

    say "ce"

    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
     tiki
    -0.09
     Avril
    -0.09
     Qi
    -0.09
     Ел
    -0.09
     reproduct
    -0.09
    LED
    -0.09
    Ey
    -0.09
     IELTS
    -0.08
     Ey
    -0.08
    EY
    -0.08
    POSITIVE LOGITS
    ce
    0.16
    .ce
    0.13
     ce
    0.13
    xce
    0.10
    cee
    0.10
    ces
    0.10
    ceria
    0.10
    _ce
    0.10
    ceiver
    0.10
    cef
    0.10
    Activations Density 0.001%

    No Known Activations