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. 11958
    Prev
    Next
    INDEX
    Explanations

    850

    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
     Fres
    -0.08
     Hof
    -0.08
    ണ
    -0.07
     Brunswick
    -0.07
     Heb
    -0.07
     Hop
    -0.07
     infection
    -0.07
     broom
    -0.07
    τευ
    -0.07
     Rin
    -0.07
    POSITIVE LOGITS
     rankings
    0.09
     gigante
    0.09
     tensors
    0.08
     discapacidad
    0.08
     relev
    0.07
     répond
    0.07
     disability
    0.07
    141
    0.07
    cand
    0.07
     Overnight
    0.07
    Activations Density 0.001%

    No Known Activations