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. 58900
    Prev
    Next
    INDEX
    Explanations

    sentence or line

    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
     mener
    -0.08
     partic
    -0.08
    दे
    -0.08
     दे
    -0.08
    且
    -0.08
     absorber
    -0.07
    -headed
    -0.07
     foil
    -0.07
    liner
    -0.07
     hechas
    -0.07
    POSITIVE LOGITS
     Fu
    0.08
    คือ
    0.08
     Juven
    0.08
     jubil
    0.07
    小学
    0.07
     Fuer
    0.07
    .tv
    0.07
    Cele
    0.07
     নেই
    0.07
    જબ
    0.07
    Activations Density 0.026%

    No Known Activations