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. 111416
    Prev
    Next
    INDEX
    Explanations

    !

    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
    ,se
    -0.09
     intime
    -0.08
     Deloitte
    -0.08
     Sewer
    -0.08
    incip
    -0.08
     অবস্থ
    -0.08
     चेहरे
    -0.08
     पाया
    -0.08
    ичные
    -0.08
     cuffs
    -0.08
    POSITIVE LOGITS
    Daniel
    0.07
     docs
    0.07
     correct
    0.07
     techniques
    0.07
    DATABASE
    0.07
     luar
    0.07
    ага
    0.07
    י
    0.07
    510
    0.07
    115
    0.07
    Activations Density 0.001%

    No Known Activations