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. 98431
    Prev
    Next
    INDEX
    Explanations

    say "if"

    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
    icked
    -0.09
    bbb
    -0.08
     crashed
    -0.07
     merging
    -0.07
    ಿಸಲಾಗ
    -0.07
    nitz
    -0.07
     surpass
    -0.07
    된
    -0.07
    ಿಸಿದ
    -0.07
    issez
    -0.07
    POSITIVE LOGITS
    ym
    0.10
    okes
    0.09
    oking
    0.09
    unts
    0.09
     feite
    0.08
     koff
    0.08
    ifle
    0.08
     arbit
    0.08
     safeguard
    0.08
     gloves
    0.08
    Activations Density 0.000%

    No Known Activations