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. 111659
    Prev
    Next
    INDEX
    Explanations

    2

    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
     Tempo
    -0.08
     briefing
    -0.07
    cun
    -0.07
    ők
    -0.07
     chiqar
    -0.07
     dois
    -0.07
    (Output
    -0.07
     byte
    -0.07
    amba
    -0.07
     Output
    -0.07
    POSITIVE LOGITS
     famosas
    0.08
    共
    0.08
     blows
    0.08
     Vand
    0.08
     共
    0.07
     experiential
    0.07
     näky
    0.07
     аль
    0.07
     сталі
    0.07
     Sans
    0.07
    Activations Density 0.013%

    No Known Activations