Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 67676
    Prev
    Next
    INDEX
    Explanations

    long

    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
     Pedro
    -0.09
     الخاصة
    -0.08
    _backup
    -0.08
    backup
    -0.08
    .elastic
    -0.08
     backup
    -0.08
     Backup
    -0.08
     plena
    -0.08
     Jason
    -0.07
     '{
    -0.07
    POSITIVE LOGITS
     permissible
    0.09
    Enough
    0.09
    Footer
    0.09
     Eta
    0.09
     ๆ
    0.08
     (>
    0.08
     voire
    0.08
     ποσ
    0.08
    هوة
    0.08
    BG
    0.08
    Activations Density 0.011%

    No Known Activations