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. 98994
    Prev
    Next
    INDEX
    Explanations

    person

    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
     surveyed
    -0.08
    ternational
    -0.08
    Enviar
    -0.08
    Hardware
    -0.07
    teenth
    -0.07
    thy
    -0.07
     purported
    -0.07
    据
    -0.07
     photographed
    -0.07
    mäß
    -0.07
    POSITIVE LOGITS
     auge
    0.08
     él
    0.08
     nesta
    0.08
     вниз
    0.08
     पुल
    0.08
     verb
    0.07
    /Post
    0.07
     محدود
    0.07
     verbs
    0.07
     songs
    0.07
    Activations Density 0.002%

    No Known Activations