© 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. 7-RESID-POST-AA
    11. 1453
    Prev
    Next
    INDEX
    Explanations

    House

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ayn
    -0.08
    ের
    -0.08
     Straw
    -0.08
     ത
    -0.08
     pivot
    -0.07
     এর
    -0.07
     conceptual
    -0.07
    �
    -0.07
     straw
    -0.07
    背
    -0.07
    POSITIVE LOGITS
    .az
    0.08
    ynyt
    0.08
    Millis
    0.07
     Plac
    0.07
    -orange
    0.07
    Plac
    0.07
    consumer
    0.07
     FIRE
    0.07
    enzi
    0.07
    OCKET
    0.07
    Activations Density 0.001%

    No Known Activations