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. 7-RESID-POST-AA
    6. 131007
    Prev
    Next
    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buddies
    -0.09
    amy
    -0.09
    .Headers
    -0.08
    Girls
    -0.08
    桌
    -0.08
     Pocket
    -0.08
     socks
    -0.08
    stash
    -0.08
    Tracks
    -0.08
     Socks
    -0.08
    POSITIVE LOGITS
     अर
    0.08
     onward
    0.08
    奉
    0.07
     उत्क
    0.07
    াস্থ
    0.07
     unsur
    0.07
    0.07
     الأرد
    0.07
     onboard
    0.07
     Renault
    0.07
    Activations Density 0.014%

    No Known Activations