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. 55834
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    �
    -0.09
    _duplicate
    -0.08
    inode
    -0.08
     वाली
    -0.08
     Eben
    -0.08
     jaune
    -0.08
     Facial
    -0.08
     Viola
    -0.08
    _PLUGIN
    -0.07
    spartner
    -0.07
    POSITIVE LOGITS
     �
    0.08
    �
    0.08
    �
    0.08
     coll
    0.07
    áil
    0.07
    (k
    0.07
     happy
    0.07
    �
    0.07
    icked
    0.07
    Ω
    0.07
    Activations Density 0.011%

    No Known Activations