Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11798
    Prev
    Next
    INDEX
    Explanations

    characters

    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
     Ul
    -0.08
    -ex
    -0.08
    गत
    -0.08
     Parque
    -0.07
    ೇಖ
    -0.07
     Weiß
    -0.07
    раж
    -0.07
     Öz
    -0.07
    盐
    -0.07
    गार
    -0.07
    POSITIVE LOGITS
     campanhas
    0.08
     சிற
    0.08
     dropdown
    0.08
     meticulously
    0.08
     preconce
    0.07
     wheels
    0.07
     મં
    0.07
    iun
    0.07
     dreamy
    0.07
     minut
    0.07
    Activations Density 0.000%

    No Known Activations