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. 29927
    Prev
    Next
    INDEX
    Explanations

    100

    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
     Pis
    -0.08
    734
    -0.08
     bos
    -0.08
    .sz
    -0.07
    Rig
    -0.07
    holds
    -0.07
     صحة
    -0.07
    astia
    -0.07
    Character
    -0.07
    Pis
    -0.07
    POSITIVE LOGITS
     (%)
    0.11
     derece
    0.09
     '%'
    0.09
    _PERCENT
    0.09
    百分
    0.09
     ശതമ
    0.09
     percentage
    0.09
     Percent
    0.08
    %。
    0.08
     प्रतिशत
    0.08
    Activations Density 0.008%

    No Known Activations