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. 58919
    Prev
    Next
    INDEX
    Explanations

    close

    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
     poč
    -0.08
     pu
    -0.08
     даст
    -0.07
    atório
    -0.07
    acons
    -0.07
     ello
    -0.07
    -0.07
    ления
    -0.07
    Fem
    -0.07
    WB
    -0.07
    POSITIVE LOGITS
     doors
    0.10
    掉
    0.09
    Door
    0.08
    -door
    0.08
     Türen
    0.08
     Tristan
    0.08
     valued
    0.08
    烟
    0.08
     apparatus
    0.08
     двер
    0.08
    Activations Density 0.030%

    No Known Activations