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. 112822
    Prev
    Next
    INDEX
    Explanations

    Asking for likes/subscriptions

    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
     excluded
    -0.08
    excluded
    -0.07
    ында
    -0.07
     exclusion
    -0.07
     dilution
    -0.07
     consumers
    -0.07
     delta
    -0.07
     zur
    -0.07
     wata
    -0.07
     fundamental
    -0.07
    POSITIVE LOGITS
     понрав
    0.11
    👏
    0.11
    👍
    0.10
     нравится
    0.10
     👍
    0.08
     successes
    0.08
    成果
    0.08
     gostei
    0.08
     نجاح
    0.08
    Gefällt
    0.08
    Activations Density 0.065%

    No Known Activations