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. 88241
    Prev
    Next
    INDEX
    Explanations

    yeah

    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
     jol
    -0.08
     crian
    -0.08
     Maestro
    -0.07
     versucht
    -0.07
    ysł
    -0.07
    islav
    -0.07
    opian
    -0.07
     ignorance
    -0.07
    ignor
    -0.07
     వే�
    -0.07
    POSITIVE LOGITS
     مخاط
    0.08
     cuales
    0.08
     đảm
    0.08
     articol
    0.07
     Buss
    0.07
    (done
    0.07
     gamers
    0.07
     Previously
    0.07
     Điều
    0.07
     whom
    0.07
    Activations Density 0.001%

    No Known Activations