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. 77292
    Prev
    Next
    INDEX
    Explanations

    positive

    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
    서는
    -0.09
     pai
    -0.08
    INATION
    -0.08
     Becky
    -0.08
    CF
    -0.08
    �
    -0.08
     stark
    -0.08
    Pc
    -0.07
     нач
    -0.07
     Pueblo
    -0.07
    POSITIVE LOGITS
     definite
    0.12
    -valu
    0.10
    -alt
    0.09
     جدًا
    0.09
    meter
    0.09
     infinity
    0.08
    -looking
    0.08
     julọ
    0.08
    -negative
    0.08
     Catal
    0.08
    Activations Density 0.037%

    No Known Activations