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. 117542
    Prev
    Next
    INDEX
    Explanations

    shape, form, appearance

    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
     Aly
    -0.07
    egna
    -0.07
     Daughter
    -0.07
     couvrir
    -0.07
     Married
    -0.07
     চলে
    -0.07
     ayrıca
    -0.07
     নিব
    -0.07
     Tog
    -0.07
     பழ
    -0.07
    POSITIVE LOGITS
     berupa
    0.14
    形式
    0.12
     형태
    0.12
     bentuk
    0.11
     guise
    0.10
     форме
    0.10
     manifested
    0.09
     виде
    0.09
     formen
    0.09
     формате
    0.08
    Activations Density 0.025%

    No Known Activations