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. 112046
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     ngoài
    -0.09
     引
    -0.09
     نە
    -0.08
     objekt
    -0.08
     tulad
    -0.08
     américaine
    -0.08
     pasted
    -0.08
     )
    -0.08
     کمتر
    -0.08
     banda
    -0.08
    POSITIVE LOGITS
     соответствии
    0.08
    Со
    0.08
     Согласно
    0.08
     અનુસાર
    0.08
     Notifications
    0.07
     Volgens
    0.07
    -original
    0.07
     Со
    0.07
     cumplimiento
    0.07
     Loy
    0.07
    Activations Density 0.051%

    No Known Activations