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. 111828
    Prev
    Next
    INDEX
    Explanations

    authentication/authorization configuration

    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
     Dice
    -0.09
    .Controls
    -0.08
    提醒
    -0.08
     Prü
    -0.08
     مرب
    -0.08
     printf
    -0.08
     Streit
    -0.08
    ühlen
    -0.08
     Taken
    -0.07
     толст
    -0.07
    POSITIVE LOGITS
     freely
    0.12
     publicly
    0.11
     공개
    0.11
    公開
    0.11
     públic
    0.10
    公开
    0.10
     gratuitement
    0.10
     pública
    0.10
     gratuitamente
    0.10
    Public
    0.10
    Activations Density 0.004%

    No Known Activations