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. 12148
    Prev
    Next
    INDEX
    Explanations

    @example

    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
     sot
    -0.09
    .interval
    -0.08
     intervals
    -0.08
     interval
    -0.08
    Interval
    -0.08
     изуч
    -0.08
     исследования
    -0.07
     Interval
    -0.07
     rh
    -0.07
    라우
    -0.07
    POSITIVE LOGITS
    メール
    0.10
     Emails
    0.10
    _example
    0.09
     beisp
    0.09
     مثال
    0.09
     präsentieren
    0.09
    Surname
    0.09
     Beispiel
    0.09
    _present
    0.09
     yüz
    0.09
    Activations Density 0.028%

    No Known Activations