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. 113988
    Prev
    Next
    INDEX
    Explanations

    |

    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
     Jep
    -0.08
     Ally
    -0.08
     sente
    -0.07
     Hendrix
    -0.07
     Hau
    -0.07
     Paige
    -0.07
    Genero
    -0.07
     almen
    -0.07
     Minh
    -0.07
    очек
    -0.07
    POSITIVE LOGITS
    âncias
    0.08
    kw
    0.08
     plaats
    0.08
    kal
    0.08
    ρω
    0.07
    αρ
    0.07
     Land
    0.07
     land
    0.07
    olocation
    0.07
     לנ
    0.07
    Activations Density 0.123%

    No Known Activations