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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 112054
    Prev
    Next
    INDEX
    Explanations

    there

    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
    ctype
    -0.08
     tritt
    -0.08
    ietta
    -0.08
    ktan
    -0.07
    _over
    -0.07
    odus
    -0.07
    -related
    -0.07
     נח
    -0.07
    oci
    -0.07
    nam
    -0.07
    POSITIVE LOGITS
     who've
    0.09
    巨大
    0.08
     Ones
    0.08
     unpublished
    0.08
     unre
    0.08
     unemployed
    0.07
     존재
    0.07
    lọwọ
    0.07
     BUY
    0.07
    もっと
    0.07
    Activations Density 0.014%

    No Known Activations