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. 58533
    Prev
    Next
    INDEX
    Explanations

    the variable J

    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
    master
    -0.08
     François
    -0.08
     Sagittarius
    -0.07
     Barbara
    -0.07
    ಚ್ಚ
    -0.07
     dzieci
    -0.07
    ें
    -0.07
    fol
    -0.07
     Linn
    -0.07
     inizi
    -0.07
    POSITIVE LOGITS
    cube
    0.09
    בל
    0.08
    _cos
    0.08
    'autant
    0.08
    )),
    ↵
    0.08
    בנ
    0.08
    qü
    0.08
     cos
    0.08
     livré
    0.08
    ’autant
    0.08
    Activations Density 0.000%

    No Known Activations