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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19153
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
     (
    -0.08
     немесе
    -0.08
     અથવા
    -0.08
     enabled
    -0.08
    &lt
    -0.07
     νέ
    -0.07
     or
    -0.07
     новые
    -0.07
    新的
    -0.07
    También
    -0.07
    POSITIVE LOGITS
     ambiguous
    0.13
     ambiguity
    0.12
    ambigu
    0.12
     definit
    0.12
     nuance
    0.12
     debated
    0.11
     nuanced
    0.11
     uncertainty
    0.11
    ichever
    0.10
     conclus
    0.10
    Activations Density 0.043%

    No Known Activations