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. 53945
    Prev
    Next
    INDEX
    Explanations

    order

    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
     trouv
    -0.09
     Aer
    -0.08
    晚
    -0.08
    underline
    -0.08
    Aer
    -0.07
     crayons
    -0.07
    乐
    -0.07
     affirm
    -0.07
    Fore
    -0.07
    ിലുള്ള
    -0.07
    POSITIVE LOGITS
     المض
    0.08
     установить
    0.08
     Bernstein
    0.07
     +/-
    0.07
    одав
    0.07
     buka
    0.07
    جابة
    0.07
     ±
    0.07
     gac
    0.07
     CNS
    0.07
    Activations Density 0.001%

    No Known Activations