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. 65114
    Prev
    Next
    INDEX
    Explanations

    recipes

    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
     interests
    -0.08
    adto
    -0.08
    elfare
    -0.08
     breasts
    -0.08
     Interests
    -0.08
     yak
    -0.08
     tecnológica
    -0.08
     योग
    -0.08
     intérêts
    -0.07
     biex
    -0.07
    POSITIVE LOGITS
     salt
    0.10
    Salt
    0.10
    salt
    0.10
    盐
    0.10
     sprinkled
    0.09
     salty
    0.09
     الطعام
    0.09
     salts
    0.09
     salted
    0.09
     খাদ
    0.09
    Activations Density 0.013%

    No Known Activations