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. 103183
    Prev
    Next
    INDEX
    Explanations

    y

    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
     Cooperative
    -0.09
     zot
    -0.09
    -own
    -0.09
     humanas
    -0.09
     cooperative
    -0.08
     Globals
    -0.08
     musikal
    -0.08
     새로운
    -0.08
     인간
    -0.08
     SENSOR
    -0.08
    POSITIVE LOGITS
     incorrectly
    0.09
     depiction
    0.09
     mistakenly
    0.08
     pict
    0.08
     correctly
    0.08
     pressed
    0.07
    sec
    0.07
     précédent
    0.07
     inaccur
    0.07
    accuracy
    0.07
    Activations Density 0.002%

    No Known Activations