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. 58944
    Prev
    Next
    INDEX
    Explanations

    Avatar The Last Airbender

    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
    सू
    -0.08
     glitter
    -0.07
     parasito
    -0.07
     graisse
    -0.07
     grass
    -0.07
     >>>
    -0.07
     Gra
    -0.07
    Hy
    -0.07
     लग
    -0.07
    incs
    -0.07
    POSITIVE LOGITS
     Refuge
    0.08
     spectaculaire
    0.08
     provider
    0.08
    _CR
    0.07
    🏻
    0.07
    🏼
    0.07
    Front
    0.07
     refugee
    0.07
     Relay
    0.07
    ப்படி
    0.07
    Activations Density 0.003%

    No Known Activations