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. 91053
    Prev
    Next
    INDEX
    Explanations

    content moderation

    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
     ECU
    -0.10
     salesman
    -0.09
    Copper
    -0.08
    mdi
    -0.08
    Equipment
    -0.08
     স্ত্রী
    -0.08
     Copper
    -0.08
    .Bar
    -0.08
     كس
    -0.08
    ähler
    -0.08
    POSITIVE LOGITS
    举报
    0.14
     curated
    0.14
     policing
    0.13
     hateful
    0.13
     censorship
    0.12
     curate
    0.12
     moderators
    0.11
     banning
    0.11
     profanity
    0.11
     editorial
    0.11
    Activations Density 0.045%

    No Known Activations