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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91719
    Prev
    Next
    INDEX
    Explanations

    consecutive 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
    dop
    -0.08
    バック
    -0.08
    इत
    -0.08
     lazım
    -0.08
     absoluta
    -0.08
     сто
    -0.08
     Krishna
    -0.07
    Genesis
    -0.07
     stoi
    -0.07
    étails
    -0.07
    POSITIVE LOGITS
     મહિલા
    0.09
     female
    0.09
     odd
    0.09
     પહ
    0.08
     vrouwelijke
    0.08
     महिला
    0.08
     perempuan
    0.08
     feminine
    0.08
     divisible
    0.08
     સંપર્ક
    0.08
    Activations Density 0.070%

    No Known Activations