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. 43678
    Prev
    Next
    INDEX
    Explanations

    .View

    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
    бі
    -0.08
     Enhanced
    -0.08
     harmon
    -0.08
     bö
    -0.08
    Coord
    -0.08
     harmonious
    -0.08
     Winds
    -0.08
    Enh
    -0.08
    ibel
    -0.07
    Enhanced
    -0.07
    POSITIVE LOGITS
    nonnull
    0.09
     acquainted
    0.08
     endle
    0.08
    bottom
    0.08
    =\
    0.08
     nipples
    0.07
     সু
    0.07
    translator
    0.07
     বুঝ
    0.07
     sellers
    0.07
    Activations Density 0.001%

    No Known Activations