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. 113801
    Prev
    Next
    INDEX
    Explanations

    Board

    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
    Usuarios
    -0.08
    -0.08
    Bloc
    -0.08
     Ci
    -0.07
     собой
    -0.07
    _ADV
    -0.07
     imposing
    -0.07
     се
    -0.07
    _adv
    -0.07
    ória
    -0.07
    POSITIVE LOGITS
    xtap
    0.09
     jule
    0.09
    杆
    0.08
     Madden
    0.08
    dị
    0.08
     Shu
    0.08
    etlen
    0.08
     tostring
    0.08
     जीव
    0.08
    gunaan
    0.08
    Activations Density 0.003%

    No Known Activations