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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 65753
    Prev
    Next
    INDEX
    Explanations

    steel

    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
     resc
    -0.09
    iex
    -0.09
     steuer
    -0.08
    暨
    -0.08
     Jain
    -0.08
    ैय
    -0.08
     gên
    -0.08
     disf
    -0.08
    īgu
    -0.08
     endogenous
    -0.08
    POSITIVE LOGITS
     chassis
    0.10
     backbone
    0.09
     мас
    0.08
     crews
    0.08
    Stamped
    0.08
    bahn
    0.08
     liners
    0.07
    .drop
    0.07
    -hard
    0.07
    Grip
    0.07
    Activations Density 0.015%

    No Known Activations