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. 98670
    Prev
    Next
    INDEX
    Explanations

    to

    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
     destacan
    -0.09
    Focus
    -0.09
    thinking
    -0.09
     Driving
    -0.09
     Think
    -0.09
    .Creat
    -0.09
    blur
    -0.08
    ��
    -0.08
     Created
    -0.08
    .Created
    -0.08
    POSITIVE LOGITS
     get
    0.20
     reach
    0.18
     earn
    0.18
     achieve
    0.16
     buy
    0.16
     make
    0.16
     win
    0.16
     finish
    0.15
     obtain
    0.15
     spend
    0.15
    Activations Density 0.073%

    No Known Activations