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. 98565
    Prev
    Next
    INDEX
    Explanations

    562

    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
    woman
    -0.08
    �്ച
    -0.07
    lete
    -0.07
    imental
    -0.07
     Mermaid
    -0.07
    못
    -0.07
    lected
    -0.07
     manj
    -0.07
    ereço
    -0.07
     vormt
    -0.07
    POSITIVE LOGITS
    562
    0.19
    56
    0.12
    563
    0.09
    _hp
    0.08
    из
    0.08
    алл
    0.07
     auxili
    0.07
     institutes
    0.07
    _cipher
    0.07
    LP
    0.07
    Activations Density 0.001%

    No Known Activations