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. 12585
    Prev
    Next
    INDEX
    Explanations

    impersonation and forgery

    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
     mense
    -0.08
     Netto
    -0.08
     Vod
    -0.08
     acumul
    -0.08
     cupboards
    -0.08
     gebeurt
    -0.07
     komst
    -0.07
    ៈ
    -0.07
     hamwe
    -0.07
     Brussel
    -0.07
    POSITIVE LOGITS
     pretending
    0.16
    欺
    0.16
     deceive
    0.15
     fraudulent
    0.15
     fake
    0.14
     fooled
    0.14
     pretend
    0.14
    骗
    0.13
     imperson
    0.13
     deception
    0.13
    Activations Density 0.037%

    No Known Activations