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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130778
    Prev
    Next
    INDEX
    Explanations

    instance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    思想
    -0.09
    ოსტ
    -0.09
    itere
    -0.08
    ոստ
    -0.08
    რთხ
    -0.08
    RESH
    -0.08
    рисида
    -0.08
     Indianapolis
    -0.08
    THON
    -0.08
     tunni
    -0.08
    POSITIVE LOGITS
    antiated
    0.16
    ality
    0.15
    aneously
    0.13
    ally
    0.12
    aneous
    0.12
    antiates
    0.12
    al
    0.11
    antiation
    0.11
    альные
    0.10
    ucional
    0.10
    Activations Density 0.042%

    No Known Activations