Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65665
    Prev
    Next
    INDEX
    Explanations

    number theory

    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
     captions
    -0.08
    /Image
    -0.07
    /Documents
    -0.07
     الحكومية
    -0.07
    /N
    -0.07
     promedio
    -0.07
     funcionarios
    -0.07
    .Func
    -0.07
     ('
    -0.07
    .Caption
    -0.07
    POSITIVE LOGITS
     decomposition
    0.13
     decom
    0.12
     primes
    0.11
     divis
    0.11
     chili
    0.10
     prime
    0.10
    Prime
    0.10
     Chili
    0.09
     divisible
    0.09
     factoring
    0.09
    Activations Density 0.095%

    No Known Activations