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. 9239
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     devastating
    -0.08
     astounding
    -0.08
    ammat
    -0.08
     catastrophic
    -0.07
     што
    -0.07
     EBITDA
    -0.07
     Megan
    -0.07
     abrupt
    -0.07
     Studi
    -0.07
     शक्त
    -0.07
    POSITIVE LOGITS
    Bread
    0.08
    ्ञान
    0.08
     Ferry
    0.08
     Brick
    0.07
    微信公众号
    0.07
    南京
    0.07
    Builtin
    0.07
    Voxel
    0.07
     Dive
    0.07
     WAY
    0.07
    Activations Density 0.014%

    No Known Activations