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. 43952
    Prev
    Next
    INDEX
    Explanations

    else

    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
     MUSIC
    -0.08
     DIS
    -0.08
    ума
    -0.08
    (DIS
    -0.08
     muda
    -0.07
     karya
    -0.07
    JECT
    -0.07
     ANG
    -0.07
     మేర
    -0.07
    olos
    -0.07
    POSITIVE LOGITS
    ajj
    0.08
     സ്ഥിര
    0.08
     Assume
    0.07
     Interview
    0.07
     بہترین
    0.07
    uila
    0.07
     رپورٹ
    0.07
     കമ്മ
    0.07
     Journ
    0.07
     Digest
    0.07
    Activations Density 0.001%

    No Known Activations