Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88278
    Prev
    Next
    INDEX
    Explanations

    Preferences, forms

    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
    ением
    -0.09
    яется
    -0.08
     Ablauf
    -0.08
     Aufgabe
    -0.08
    seau
    -0.08
     doğru
    -0.08
    ению
    -0.08
    ляются
    -0.08
     avulla
    -0.08
     основании
    -0.08
    POSITIVE LOGITS
     предпоч
    0.18
     preference
    0.17
     prefere
    0.17
     prefer
    0.17
     preferences
    0.17
    Preference
    0.17
     preferred
    0.16
     voorkeur
    0.16
     Preference
    0.15
     prefers
    0.15
    Activations Density 0.104%

    No Known Activations