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. 15-RESID-POST-AA
    6. 18723
    Prev
    Next
    INDEX
    Explanations

    says

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eba
    -0.08
     anderen
    -0.08
     മറ്റ
    -0.08
     eva
    -0.07
     മറ്റു
    -0.07
     altri
    -0.07
    unts
    -0.07
     തട
    -0.07
     andra
    -0.07
    ,j
    -0.07
    POSITIVE LOGITS
    却
    0.11
     Parece
    0.10
    Veuillez
    0.10
     nevertheless
    0.09
     lại
    0.09
    народ
    0.09
     pourtant
    0.08
    !!!!
    0.08
    گ
    0.08
     allegedly
    0.08
    Activations Density 0.022%

    No Known Activations