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. 23-RESID-POST-AA
    6. 98328
    Prev
    Next
    INDEX
    Explanations

    job appointments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    듯
    -0.09
    utable
    -0.08
    �
    -0.08
    �
    -0.08
    female
    -0.08
    ර
    -0.08
    كما
    -0.08
    그리고
    -0.07
    ácil
    -0.07
     auxqu
    -0.07
    POSITIVE LOGITS
     appointed
    0.22
     selected
    0.19
     hired
    0.17
     elected
    0.17
     nominated
    0.16
     awarded
    0.16
     chosen
    0.16
     assigned
    0.16
     promoted
    0.16
     granted
    0.16
    Activations Density 0.079%

    No Known Activations