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. 11-RESID-POST-AA
    6. 120397
    Prev
    Next
    INDEX
    Explanations

    passage of time

    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
    -là
    -0.08
     باب
    -0.08
     boolean
    -0.08
    -striped
    -0.08
     gboolean
    -0.08
     BOOL
    -0.08
    -level
    -0.08
     preferência
    -0.08
     enabled
    -0.08
    andisa
    -0.07
    POSITIVE LOGITS
    多久
    0.12
     decades
    0.12
    Elapsed
    0.11
    Years
    0.11
     longtemps
    0.11
     elapsed
    0.11
    久
    0.11
     ago
    0.11
    多年
    0.11
     वर्षों
    0.10
    Activations Density 0.033%

    No Known Activations