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. 7-RESID-POST-AA
    6. 131018
    Prev
    Next
    INDEX
    Explanations

    temporal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mantle
    -0.08
     fore
    -0.07
    Hak
    -0.07
     probing
    -0.07
     Pf
    -0.07
     LTD
    -0.07
     okus
    -0.07
    adc
    -0.07
     Stacy
    -0.07
     ec
    -0.07
    POSITIVE LOGITS
    轴
    0.08
     Roh
    0.07
     rope
    0.07
     beleids
    0.07
     illusions
    0.07
     foe
    0.07
     Hö
    0.07
     hoid
    0.07
    _lib
    0.07
     Paw
    0.07
    Activations Density 0.002%

    No Known Activations