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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43946
    Prev
    Next
    INDEX
    Explanations

    gullibility, scams

    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
    jima
    -0.08
    reb
    -0.08
     Constraints
    -0.08
    onym
    -0.07
    ces
    -0.07
    xygen
    -0.07
    emer
    -0.07
    str
    -0.07
     MIX
    -0.07
    anay
    -0.07
    POSITIVE LOGITS
     believing
    0.11
     blindly
    0.11
     fooled
    0.10
     naï
    0.10
     misinformation
    0.10
     misguided
    0.10
     crey
    0.10
     trusting
    0.10
    被骗
    0.09
     vào
    0.09
    Activations Density 0.051%

    No Known Activations