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. 98375
    Prev
    Next
    INDEX
    Explanations

    Math symbols

    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
    _NET
    -0.08
     soq
    -0.08
     feela
    -0.08
    [_
    -0.08
     bilan
    -0.07
    va
    -0.07
    Qo
    -0.07
    olta
    -0.07
     પોતાના
    -0.07
    .v
    -0.07
    POSITIVE LOGITS
     \(
    0.12
    \(
    0.10
     $
    0.10
     approximately
    0.09
    ≈
    0.09
     irrational
    0.08
     تقریب
    0.08
     approx
    0.08
    approx
    0.08
     yaklaşık
    0.08
    Activations Density 0.109%

    No Known Activations