Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77305
    Prev
    Next
    INDEX
    Explanations

    period

    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
     TPS
    -0.08
     PCP
    -0.08
    PSC
    -0.08
     কিন
    -0.08
     এটি
    -0.08
     PSC
    -0.08
     PSL
    -0.08
     Tb
    -0.08
     kişinin
    -0.08
    ھر
    -0.07
    POSITIVE LOGITS
     seep
    0.09
     ನೀಡಿ
    0.08
     näk
    0.08
    בחר
    0.07
    ात्मक
    0.07
     grout
    0.07
    記事
    0.07
     gider
    0.07
    jet
    0.07
     sowie
    0.07
    Activations Density 0.076%

    No Known Activations