© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2787
    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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    558
    -0.08
     vu
    -0.07
     lager
    -0.07
     Neues
    -0.07
    yet
    -0.07
     �
    -0.07
    gulp
    -0.07
     Gerald
    -0.07
     Licht
    -0.07
     wass
    -0.07
    POSITIVE LOGITS
     adherence
    0.08
     Korn
    0.07
     Carbon
    0.07
     conscious
    0.07
     Kare
    0.07
     эк
    0.07
    уна
    0.07
     Stu
    0.07
     completed
    0.07
    cess
    0.07
    Activations Density 0.036%

    No Known Activations