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. 113952
    Prev
    Next
    INDEX
    Explanations

    Completing sentences/statements

    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
     toege
    -0.08
     permanente
    -0.08
     Metall
    -0.07
    .Features
    -0.07
     metall
    -0.07
     Мет
    -0.07
     permanent
    -0.07
    Phong
    -0.07
    -friendly
    -0.07
     forfait
    -0.07
    POSITIVE LOGITS
     completar
    0.17
     incomplete
    0.15
    _completion
    0.15
    Completion
    0.15
    Incomplete
    0.14
     compléter
    0.14
     unfinished
    0.14
     complet
    0.14
     completion
    0.14
     completing
    0.14
    Activations Density 0.136%

    No Known Activations