Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8916
    Prev
    Next
    INDEX
    Explanations

    phase

    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
     во
    -0.08
     Lind
    -0.07
     För
    -0.07
    त्र
    -0.07
     દેખ
    -0.07
     antiques
    -0.07
    Muk
    -0.07
     Rast
    -0.07
    ающий
    -0.07
    게
    -0.07
    POSITIVE LOGITS
     із
    0.09
    -adjust
    0.08
     nem
    0.08
    Adjustment
    0.08
     وأن
    0.08
     Adjustment
    0.07
     figuring
    0.07
     Californ
    0.07
     Sonata
    0.07
     pv
    0.07
    Activations Density 0.003%

    No Known Activations