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. 76523
    Prev
    Next
    INDEX
    Explanations

    ex

    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
     kan
    -0.08
     війсь
    -0.08
    .Lerp
    -0.07
     aboard
    -0.07
    城乡
    -0.07
     Dim
    -0.07
     arche
    -0.07
     Electrical
    -0.07
    -0.07
     чита
    -0.07
    POSITIVE LOGITS
    দের
    0.08
     handsome
    0.08
     remov
    0.08
     solu
    0.08
    াতিক
    0.08
     menú
    0.08
     عنه
    0.07
    ологиялық
    0.07
     sacrific
    0.07
     disg
    0.07
    Activations Density 0.001%

    No Known Activations