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. 76670
    Prev
    Next
    INDEX
    Explanations

    offensive language

    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
     전망
    -0.08
    iyana
    -0.08
     tantal
    -0.08
    ISION
    -0.08
    ifye
    -0.07
    हम
    -0.07
    MEA
    -0.07
    丰富
    -0.07
     temos
    -0.07
     malik
    -0.07
    POSITIVE LOGITS
     crap
    0.12
     stupid
    0.10
     fool
    0.09
     idiots
    0.09
     nonsense
    0.09
     incompet
    0.08
     bastard
    0.08
     jargon
    0.08
    ???
    0.08
     incompetent
    0.08
    Activations Density 0.240%

    No Known Activations