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. 60816
    Prev
    Next
    INDEX
    Explanations

    to

    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
    олч
    -0.09
     Dont
    -0.09
     lingering
    -0.08
     prow
    -0.08
     Tuc
    -0.08
     Trump
    -0.08
     incluida
    -0.08
     lag
    -0.08
     bụ
    -0.08
     ce
    -0.08
    POSITIVE LOGITS
     exp
    0.09
     constructing
    0.08
    exp
    0.08
     drafting
    0.08
     الآ
    0.07
     Erstellung
    0.07
     создание
    0.07
     escre
    0.07
     elucid
    0.07
     அல
    0.07
    Activations Density 0.010%

    No Known Activations