© 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. 78899
    Prev
    Next
    INDEX
    Explanations

    math equations, solutions

    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
    pixels
    -0.08
     prz
    -0.08
     limpa
    -0.07
     fẹ
    -0.07
    chunks
    -0.07
    _pixels
    -0.07
    .prototype
    -0.07
     вмест
    -0.07
     مياه
    -0.07
     puree
    -0.07
    POSITIVE LOGITS
     الثلاث
    0.09
    entrant
    0.08
     Beginner
    0.08
     negatieve
    0.08
    前三
    0.08
     onmiddell
    0.08
     zelfstand
    0.08
     chase
    0.08
    فرادی
    0.08
    Referral
    0.08
    Activations Density 0.005%

    No Known Activations