© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12721
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.08
    erges
    -0.08
    blend
    -0.08
    poster
    -0.08
    ilter
    -0.07
     направ
    -0.07
    895
    -0.07
    borrow
    -0.07
    сли
    -0.07
    পুর
    -0.07
    POSITIVE LOGITS
    宗
    0.08
     delicious
    0.08
     Rip
    0.08
     tasty
    0.08
    ாளர்
    0.08
     Dangerous
    0.08
     recipe
    0.07
    吃
    0.07
    (J
    0.07
     delightful
    0.07
    Activations Density 0.001%

    No Known Activations