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. 77563
    Prev
    Next
    INDEX
    Explanations

    face masks

    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
     tramp
    -0.07
     magical
    -0.07
     msg
    -0.07
     மேல
    -0.07
     elements
    -0.07
    Autom
    -0.07
     Lisp
    -0.07
     Game
    -0.07
     parallel
    -0.07
     tel
    -0.07
    POSITIVE LOGITS
     коронавирус
    0.10
     کورونا
    0.10
     ventilation
    0.09
    /pass
    0.09
     respir
    0.09
     respirar
    0.09
     Respir
    0.09
    /privacy
    0.09
     Foi
    0.09
     coronavírus
    0.09
    Activations Density 0.009%

    No Known Activations