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. 44152
    Prev
    Next
    INDEX
    Explanations

    polynomial equations, integers

    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
     Hang
    -0.08
    ::_
    -0.08
    		↵		↵
    -0.08
     ministra
    -0.08
     stress
    -0.08
    强调
    -0.07
    		↵		↵		↵
    -0.07
     kwest
    -0.07
     emphasizes
    -0.07
    stress
    -0.07
    POSITIVE LOGITS
     coefficients
    0.11
    coeff
    0.11
    _coeff
    0.10
     coeff
    0.10
    Coe
    0.10
     coef
    0.09
     коэффици
    0.08
     सार्वजनिक
    0.08
    Digits
    0.08
     જાહેર
    0.08
    Activations Density 0.013%

    No Known Activations