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. 76685
    Prev
    Next
    INDEX
    Explanations

    P

    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
     mice
    -0.08
     fungi
    -0.08
     Fuse
    -0.07
     Owl
    -0.07
     stitch
    -0.07
    erea
    -0.07
     mouse
    -0.07
    erein
    -0.07
     Campeonato
    -0.07
     mout
    -0.07
    POSITIVE LOGITS
    本金
    0.13
    金额
    0.11
     টাকা
    0.11
     रकम
    0.11
     राशि
    0.10
     mikt
    0.10
     \$
    0.10
     مبلغ
    0.10
     (€
    0.10
     ₹
    0.10
    Activations Density 0.033%

    No Known Activations