© 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. 250
    Prev
    Next
    INDEX
    Explanations

    Habit stacking

    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
     heav
    -0.08
     heavy
    -0.08
     sto
    -0.08
    и
    -0.07
    heavy
    -0.07
    驶
    -0.07
     Sto
    -0.07
     toxic
    -0.07
    with
    -0.07
    ters
    -0.07
    POSITIVE LOGITS
    -trigger
    0.09
     paikka
    0.08
     הכי
    0.08
     장소
    0.08
    _CODES
    0.08
     quale
    0.08
    'ordre
    0.08
     ordine
    0.08
     Ord
    0.08
     Hotels
    0.08
    Activations Density 0.009%

    No Known Activations