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. 103017
    Prev
    Next
    INDEX
    Explanations

    trailing

    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
    এই
    -0.08
    ierz
    -0.08
     тези
    -0.08
     fabricantes
    -0.08
     modos
    -0.08
     tentu
    -0.08
     forskning
    -0.08
    omo
    -0.08
     ergonom
    -0.08
     repair
    -0.07
    POSITIVE LOGITS
     offset
    0.08
     Offset
    0.08
    ollows
    0.08
    _OFFSET
    0.08
    offset
    0.07
     Hebrews
    0.07
     Byr
    0.07
     OFFSET
    0.07
     offsets
    0.07
    -offset
    0.07
    Activations Density 0.001%

    No Known Activations