© 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. 11-RESID-POST-AA
    11. 75608
    Prev
    Next
    INDEX
    Explanations

    i

    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
    Limits
    -0.08
     влияние
    -0.07
    decoded
    -0.07
     অ
    -0.07
     intermediary
    -0.07
    individual
    -0.07
    ்சி
    -0.07
     أثر
    -0.07
    ்கு
    -0.07
    net
    -0.07
    POSITIVE LOGITS
     deeds
    0.08
    ізацыі
    0.08
     festa
    0.08
     tib
    0.08
     తెలిప
    0.08
     métal
    0.08
     Renderer
    0.08
     feest
    0.08
    !!!!!!
    0.08
    �
    0.08
    Activations Density 0.001%

    No Known Activations