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. 15-RESID-POST-AA
    6. 19235
    Prev
    Next
    INDEX
    Explanations

    analog

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _mix
    -0.08
    混
    -0.08
    Remote
    -0.08
     mezcla
    -0.08
     mixture
    -0.08
     mix
    -0.08
     Mischung
    -0.07
    Mixin
    -0.07
     DN
    -0.07
     mistura
    -0.07
    POSITIVE LOGITS
     analogy
    0.10
     analog
    0.09
    应该
    0.09
     analogous
    0.09
    analog
    0.09
    rito
    0.09
     aesthetically
    0.09
    Analog
    0.08
     logically
    0.08
    應
    0.08
    Activations Density 0.008%

    No Known Activations