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. 98661
    Prev
    Next
    INDEX
    Explanations

    ец

    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
     Archer
    -0.08
    ці
    -0.08
    fle
    -0.08
    cline
    -0.07
     retry
    -0.07
     Art
    -0.07
     Fly
    -0.07
     overpower
    -0.07
    Art
    -0.07
    solid
    -0.07
    POSITIVE LOGITS
    ీరో
    0.11
    ెంబ
    0.09
    ివ్
    0.09
    ензи
    0.09
    enzen
    0.09
    yzda
    0.08
    ె
    0.08
    енз
    0.08
     oom
    0.08
    еҙ
    0.08
    Activations Density 0.000%

    No Known Activations