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. 42095
    Prev
    Next
    INDEX
    Explanations

    potion

    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
     hurdles
    -0.09
    障
    -0.08
     Gurb
    -0.08
    usst
    -0.08
    缘
    -0.08
    .directive
    -0.08
     adn
    -0.08
    .Infrastructure
    -0.08
     lieb
    -0.07
    .block
    -0.07
    POSITIVE LOGITS
     conco
    0.15
     brewed
    0.12
     brew
    0.11
     potion
    0.10
     Potion
    0.10
     cocktails
    0.10
     mixtures
    0.09
     смесь
    0.09
    готавли
    0.09
     vloe
    0.09
    Activations Density 0.006%

    No Known Activations