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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29850
    Prev
    Next
    INDEX
    Explanations

    number theory

    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
     Kobe
    -0.08
     Pamela
    -0.08
     plagued
    -0.08
    atero
    -0.08
     Mans
    -0.08
     alcohol
    -0.07
    -circle
    -0.07
     tap
    -0.07
    (circle
    -0.07
     ansiedad
    -0.07
    POSITIVE LOGITS
     gcd
    0.10
    .extract
    0.08
    Uuid
    0.08
    Adaptor
    0.08
     gemeinsame
    0.08
     cok
    0.08
     соглас
    0.07
     UU
    0.07
     Basement
    0.07
    |null
    0.07
    Activations Density 0.018%

    No Known Activations