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. 88341
    Prev
    Next
    INDEX
    Explanations

    the

    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
     नौ
    -0.08
     imin
    -0.07
     compiler
    -0.07
     جلد
    -0.07
     이동
    -0.07
     نیم
    -0.07
     网
    -0.07
     vano
    -0.07
     vire
    -0.07
    (net
    -0.07
    POSITIVE LOGITS
     grieving
    0.10
     sobri
    0.08
     responsabil
    0.08
    _DIPSETTING
    0.08
    .property
    0.08
     grievance
    0.08
     spiritual
    0.08
     эмоцион
    0.08
     emotional
    0.08
     emo
    0.08
    Activations Density 0.016%

    No Known Activations