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. 53129
    Prev
    Next
    INDEX
    Explanations

    ((

    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
    logo
    -0.08
     nyaéta
    -0.08
     slog
    -0.08
     grafik
    -0.07
    �
    -0.07
    く
    -0.07
    弃
    -0.07
     cad
    -0.07
    Crunch
    -0.07
    \v
    -0.07
    POSITIVE LOGITS
     Provision
    0.08
     consequent
    0.08
     hát
    0.08
    ETIME
    0.07
    _PHASE
    0.07
     accordance
    0.07
     facil
    0.07
     Subse
    0.07
     tổng
    0.07
     Elect
    0.07
    Activations Density 0.001%

    No Known Activations