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. 58804
    Prev
    Next
    INDEX
    Explanations

    trophy

    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
     wakati
    -0.09
     injection
    -0.08
    Injection
    -0.08
     injecting
    -0.08
    cherche
    -0.08
     Injection
    -0.08
     لخوا
    -0.08
     passwords
    -0.08
    Inject
    -0.08
    guise
    -0.08
    POSITIVE LOGITS
     trophies
    0.14
     trophy
    0.13
    奖
    0.13
     awarded
    0.12
     awarding
    0.12
     पुरस्कार
    0.11
     awards
    0.11
     medals
    0.10
    奖金
    0.10
    奖励
    0.10
    Activations Density 0.015%

    No Known Activations