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. 120259
    Prev
    Next
    INDEX
    Explanations

    Green

    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
    Opacity
    -0.08
     drast
    -0.08
    -opacity
    -0.08
    �
    -0.07
     задерж
    -0.07
    ส
    -0.07
     prz
    -0.07
     nettet
    -0.07
     الصور
    -0.07
    נת
    -0.07
    POSITIVE LOGITS
     Tibetan
    0.08
    0.08
    .lastname
    0.08
     Bast
    0.08
     parcialmente
    0.07
    ṛ
    0.07
     Bells
    0.07
     Screw
    0.07
    消防
    0.07
     Kashmir
    0.07
    Activations Density 0.002%

    No Known Activations