Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 630
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    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
     yollar
    -0.09
    Bydd
    -0.09
     vreemd
    -0.09
     vre
    -0.09
     karere
    -0.09
    =headers
    -0.09
    Nunca
    -0.09
     Müdürlüğ
    -0.09
     vreemde
    -0.08
    Mb
    -0.08
    POSITIVE LOGITS
     refers
    0.07
    0.07
    字
    0.07
     gen
    0.07
    421
    0.07
    语
    0.07
     means
    0.06
     _
    0.06
     often
    0.06
     plan
    0.06
    Activations Density 0.089%

    No Known Activations