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. 77476
    Prev
    Next
    INDEX
    Explanations

    Moving up

    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
    PO
    -0.08
    Men
    -0.08
    ICP
    -0.08
    think
    -0.08
    amul
    -0.07
     oluline
    -0.07
    メ
    -0.07
     reconnaissance
    -0.07
     matéria
    -0.07
    ircuit
    -0.07
    POSITIVE LOGITS
     ואת
    0.09
     చేసి
    0.09
     다시
    0.09
    lasht
    0.08
     מחדש
    0.08
     fullest
    0.08
    вати
    0.08
     paylaş
    0.08
     destabil
    0.08
     möglichst
    0.08
    Activations Density 0.176%

    No Known Activations