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. 43944
    Prev
    Next
    INDEX
    Explanations

    not

    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
     тол
    -0.08
     бли
    -0.07
     இர
    -0.07
     Strasbourg
    -0.07
     터
    -0.07
     любого
    -0.07
    bindung
    -0.07
     World
    -0.07
     कभी
    -0.07
     --------------------------------
    -0.07
    POSITIVE LOGITS
     messed
    0.10
     presumably
    0.08
    That's
    0.08
     refers
    0.08
    蛋
    0.07
    Mortgage
    0.07
     offenbar
    0.07
    Rpc
    0.07
     Explosion
    0.07
    umably
    0.07
    Activations Density 0.312%

    No Known Activations