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. 65727
    Prev
    Next
    INDEX
    Explanations

    atory

    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
     optimal
    -0.08
    Optimal
    -0.08
     Optimal
    -0.08
     aerobic
    -0.07
    VID
    -0.07
     UID
    -0.07
    Life
    -0.07
     antioxidant
    -0.07
     SYS
    -0.07
     UIS
    -0.07
    POSITIVE LOGITS
     profanity
    0.11
     offend
    0.10
     defamatory
    0.10
     prejud
    0.10
     derog
    0.09
    خواه
    0.09
     вред
    0.09
    ご了承ください
    0.09
     prejudice
    0.09
     risque
    0.09
    Activations Density 0.009%

    No Known Activations