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. 102759
    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
     энер
    -0.08
                                                                      
    -0.08
    数据显示
    -0.08
     seks
    -0.08
    風吹
    -0.08
     purposeful
    -0.07
     auftreten
    -0.07
     Гар
    -0.07
     Parties
    -0.07
    ecurities
    -0.07
    POSITIVE LOGITS
    quoted
    0.08
    Lon
    0.08
    012
    0.08
    افات
    0.07
    (drop
    0.07
     discussed
    0.07
    issed
    0.07
    /month
    0.07
    vv
    0.07
    =my
    0.07
    Activations Density 0.000%

    No Known Activations