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. 46930
    Prev
    Next
    INDEX
    Explanations

    land formations

    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
     মাত
    -0.08
     dissemination
    -0.07
    emente
    -0.07
     sophisticated
    -0.07
    াদ
    -0.07
    PU
    -0.07
    ...)
    -0.07
     পরিচাল
    -0.07
    操
    -0.07
     lourd
    -0.07
    POSITIVE LOGITS
     carved
    0.13
     cavities
    0.10
     recessed
    0.10
     etched
    0.09
     lumen
    0.09
     holl
    0.09
     carve
    0.09
     trenches
    0.09
     creada
    0.09
     emptied
    0.09
    Activations Density 0.049%

    No Known Activations