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. 130967
    Prev
    Next
    INDEX
    Explanations

    S

    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
    uksen
    -0.09
    اهرة
    -0.08
     کرده
    -0.08
     காண
    -0.08
     guste
    -0.08
     jobject
    -0.08
     श्रेष्ठ
    -0.08
    аи
    -0.08
     کامی
    -0.08
     nug
    -0.08
    POSITIVE LOGITS
     sash
    0.09
    Dash
    0.08
     dash
    0.08
    'Al
    0.08
    .team
    0.08
    edo
    0.08
     Dash
    0.08
     suspensão
    0.07
    ash
    0.07
    _dash
    0.07
    Activations Density 0.002%

    No Known Activations