Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19029
    Prev
    Next
    INDEX
    Explanations

    tangent

    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
     overtime
    -0.08
    34
    -0.08
     Limp
    -0.07
     glitch
    -0.07
     sahip
    -0.07
    _OCCURRED
    -0.07
    58
    -0.07
    �
    -0.07
     silêncio
    -0.07
     cosplay
    -0.07
    POSITIVE LOGITS
    ’ub
    0.09
     touching
    0.09
     intersects
    0.09
     intersections
    0.09
     Zowel
    0.09
    -touch
    0.09
     Baxter
    0.09
     مدارس
    0.08
     Diane
    0.08
     Henry
    0.08
    Activations Density 0.009%

    No Known Activations