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. 58910
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
    Partition
    -0.08
    -0.07
    _i
    -0.07
    _partition
    -0.07
     ninguém
    -0.07
    ofs
    -0.07
    ARNING
    -0.07
    尔
    -0.07
    IF
    -0.07
     aangek
    -0.07
    POSITIVE LOGITS
     angka
    0.08
     DNI
    0.08
     alqu
    0.08
     Lottery
    0.08
     LIC
    0.08
     Amateur
    0.08
    -digit
    0.08
    કોટ
    0.08
     anseo
    0.07
     الشاشة
    0.07
    Activations Density 0.016%

    No Known Activations