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. 11-RESID-POST-AA
    6. 12849
    Prev
    Next
    INDEX
    Explanations

    Digits 0 and 1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -covered
    -0.08
    ама
    -0.08
     Anc
    -0.07
    esch
    -0.07
    ‹
    -0.07
    èk
    -0.07
    هم
    -0.07
    ),
    -0.07
    ’était
    -0.07
     slap
    -0.07
    POSITIVE LOGITS
     എന്നിവ
    0.11
     എന്നീ
    0.10
     ஆகிய
    0.10
     alike
    0.09
     എന്നിവർ
    0.08
     Weil
    0.08
    Kab
    0.08
     birbir
    0.08
    ൈവ
    0.08
     그리고
    0.08
    Activations Density 0.035%

    No Known Activations