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. 54152
    Prev
    Next
    INDEX
    Explanations

    but

    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
     કલ
    -0.08
     venn
    -0.08
    teen
    -0.08
    urations
    -0.08
     interpersonal
    -0.07
    .Switch
    -0.07
     passende
    -0.07
    .bo
    -0.07
     പോലും
    -0.07
     letan
    -0.07
    POSITIVE LOGITS
     Wid
    0.08
    reiber
    0.07
     Sho
    0.07
    虹
    0.07
    িজ্ঞ
    0.07
    ’re
    0.07
    wid
    0.07
    规律
    0.07
    _rr
    0.07
     Beob
    0.07
    Activations Density 0.013%

    No Known Activations