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. 60757
    Prev
    Next
    INDEX
    Explanations

    magnetic

    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
     halk
    -0.08
     Vila
    -0.08
     justa
    -0.08
    zięki
    -0.08
    setw
    -0.08
     vcs
    -0.08
     phare
    -0.08
     Colise
    -0.08
    ਸ਼
    -0.07
     Rene
    -0.07
    POSITIVE LOGITS
    itone
    0.09
    igu
    0.08
    compatible
    0.08
     compatible
    0.08
    isible
    0.08
     detectable
    0.08
    _types
    0.07
    iguous
    0.07
     types
    0.07
    licable
    0.07
    Activations Density 0.004%

    No Known Activations