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. 452
    Prev
    Next
    INDEX
    Explanations

    Pumped hydro energy storage

    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
     Treff
    -0.09
    ptable
    -0.08
    总
    -0.08
     Printable
    -0.08
     deepcopy
    -0.08
     doxy
    -0.08
     CPP
    -0.08
    drawable
    -0.08
     cop
    -0.08
     총
    -0.08
    POSITIVE LOGITS
     సాగ
    0.08
     ప్రవ
    0.08
     uiteen
    0.08
    φέρ
    0.08
     sjón
    0.07
     fietsen
    0.07
     seo
    0.07
     skyscr
    0.07
     onderweg
    0.07
     ayant
    0.07
    Activations Density 0.001%

    No Known Activations