© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54719
    Prev
    Next
    INDEX
    Explanations

    mathematical parity reasoning

    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
    學
    -0.10
    학
    -0.08
    学
    -0.07
    _reference
    -0.07
    名
    -0.07
     क्ष
    -0.07
    orrido
    -0.07
    参考
    -0.07
    用途
    -0.07
    (";
    -0.07
    POSITIVE LOGITS
     parity
    0.09
     tame
    0.09
     televiz
    0.09
     divisible
    0.08
     ciphertext
    0.08
     gabi
    0.08
    .randint
    0.08
    Neill
    0.08
     randint
    0.08
     sisi
    0.08
    Activations Density 0.041%

    No Known Activations