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. 98988
    Prev
    Next
    INDEX
    Explanations

    Enumerated items with brackets

    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
    ிலை
    -0.09
     Blockly
    -0.09
     승인
    -0.09
    லி
    -0.09
     potencial
    -0.09
    potential
    -0.08
    opu
    -0.08
    upy
    -0.08
    िली
    -0.08
    okable
    -0.08
    POSITIVE LOGITS
     sør
    0.08
     الأم
    0.08
     shall
    0.08
    ăr
    0.07
     nex
    0.07
    xi
    0.07
     •
    0.07
    dresser
    0.07
    ……
    0.07
    ,,
    0.07
    Activations Density 0.026%

    No Known Activations