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. 98399
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ieving
    -0.08
     jour
    -0.07
     DA
    -0.07
     sociedades
    -0.07
     développe
    -0.07
     modu
    -0.07
     Cauc
    -0.07
     desenvol
    -0.07
     devlet
    -0.07
     zust
    -0.07
    POSITIVE LOGITS
    338
    0.08
    686
    0.08
    685
    0.08
    339
    0.08
    Sharp
    0.08
    418
    0.08
    ẹlu
    0.08
     αι
    0.07
    hina
    0.07
    point
    0.07
    Activations Density 0.001%

    No Known Activations