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. 112276
    Prev
    Next
    INDEX
    Explanations

    asterisk

    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
     decades
    -0.09
    wart
    -0.08
     gior
    -0.08
     lectures
    -0.08
     decade
    -0.08
     necessity
    -0.08
    .Context
    -0.07
    ನಿವಾರ
    -0.07
     days
    -0.07
     wad
    -0.07
    POSITIVE LOGITS
    ذية
    0.09
     copro
    0.08
     Pivot
    0.08
     крест
    0.08
     eign
    0.08
     MSS
    0.08
     Mysql
    0.08
    赚钱
    0.08
     수행
    0.07
    াঙ
    0.07
    Activations Density 0.014%

    No Known Activations