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. 3-RESID-POST-AA
    6. 12459
    Prev
    Next
    INDEX
    Explanations

    -minded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Elem
    -0.07
     airing
    -0.07
     gutt
    -0.07
    Ingredient
    -0.07
    Imports
    -0.07
     bleach
    -0.07
    fetch
    -0.07
     спраш
    -0.07
    minor
    -0.07
    Leaks
    -0.07
    POSITIVE LOGITS
     Toul
    0.09
     �
    0.09
     Cham
    0.08
     Barg
    0.07
     Wor
    0.07
     Turkish
    0.07
    sure
    0.07
     Joachim
    0.07
    Sw
    0.07
     Romney
    0.07
    Activations Density 0.001%

    No Known Activations