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. 23-RESID-POST-AA
    6. 130899
    Prev
    Next
    INDEX
    Explanations

    Code configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sime
    -0.08
     subordinate
    -0.08
     Context
    -0.08
     earth
    -0.08
    (Context
    -0.08
     gedachten
    -0.08
    迅雷
    -0.08
     Kontext
    -0.08
    тан
    -0.08
     aarde
    -0.07
    POSITIVE LOGITS
     zug
    0.08
    (cors
    0.08
    Loose
    0.08
     Vermont
    0.08
    _per
    0.07
    Caught
    0.07
     cím
    0.07
     gestione
    0.07
    .handle
    0.07
    Captured
    0.07
    Activations Density 0.003%

    No Known Activations