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. 56190
    Prev
    Next
    INDEX
    Explanations

    potential offensive statements

    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
    bass
    -0.08
     toilets
    -0.08
     확보
    -0.07
    lange
    -0.07
     ежегод
    -0.07
     record
    -0.07
    pod
    -0.07
     Чем
    -0.07
     Verified
    -0.07
     pharmacies
    -0.07
    POSITIVE LOGITS
     ofens
    0.13
     offend
    0.13
     offended
    0.13
     inadvert
    0.13
     offending
    0.12
     interpretations
    0.12
     harassment
    0.12
     sarcas
    0.12
     offensive
    0.11
     unintended
    0.11
    Activations Density 0.069%

    No Known Activations