© 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. 47959
    Prev
    Next
    INDEX
    Explanations

    symbol

    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
    oran
    -0.08
     fin
    -0.08
     quin
    -0.07
    其中
    -0.07
     honest
    -0.07
     assaults
    -0.07
    berry
    -0.07
     assault
    -0.07
     delin
    -0.07
    မာ
    -0.07
    POSITIVE LOGITS
    ांकन
    0.10
     USED
    0.08
     représentant
    0.08
    (Symbol
    0.08
    acters
    0.08
    (symbol
    0.08
     exchanged
    0.08
     Symbol
    0.07
    .symbol
    0.07
     derby
    0.07
    Activations Density 0.008%

    No Known Activations