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. 130846
    Prev
    Next
    INDEX
    Explanations

    foreign script

    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
     संत
    -0.08
     快乐
    -0.07
    ارن
    -0.07
     urge
    -0.07
     جودة
    -0.07
     Thanks
    -0.07
     Soul
    -0.07
     verlang
    -0.07
     QUALITY
    -0.07
     ⭐
    -0.07
    POSITIVE LOGITS
     veniam
    0.08
    (Custom
    0.08
    .user
    0.08
     Sliding
    0.08
    энні
    0.08
    энне
    0.08
    ляя
    0.08
    Custom
    0.08
    лением
    0.08
    _Custom
    0.08
    Activations Density 0.000%

    No Known Activations