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. 15-RESID-POST-AA
    6. 18975
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
     etc
    -0.14
     Also
    -0.12
     વગેરે
    -0.11
    -0.11
     таксама
    -0.11
     samuti
    -0.11
    -0.11
     आदि
    -0.10
    -0.10
    ികളും
    -0.10
    POSITIVE LOGITS
    e
    0.19
    ी
    0.16
     for
    0.15
    ,
    0.15
    i
    0.15
    ੀ
    0.14
    ી
    0.14
    y
    0.14
    o
    0.13
    "
    0.13
    Activations Density 0.308%

    No Known Activations