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. 58802
    Prev
    Next
    INDEX
    Explanations

    market entry/exit

    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
    houding
    -0.09
    Sequential
    -0.07
     Rustic
    -0.07
     Sequential
    -0.07
     mask
    -0.07
    mask
    -0.07
     Caps
    -0.07
     Active
    -0.07
    идан
    -0.07
     Attachment
    -0.07
    POSITIVE LOGITS
    uatan
    0.10
     adjusting
    0.08
     influx
    0.08
     pun
    0.08
    =require
    0.08
     profitable
    0.08
     خواهد
    0.08
    adding
    0.08
    ปร
    0.08
    ാകും
    0.08
    Activations Density 0.003%

    No Known Activations