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. 130371
    Prev
    Next
    INDEX
    Explanations

    commercial entities

    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
    gaven
    -0.08
     прекрас
    -0.08
     заявки
    -0.08
    lah
    -0.08
    lösung
    -0.08
    കെ
    -0.08
     ascertain
    -0.08
     настоящ
    -0.08
     debit
    -0.07
    peek
    -0.07
    POSITIVE LOGITS
    或者
    0.11
     namens
    0.09
    或
    0.09
     oder
    0.09
     یا
    0.09
    たり
    0.08
    有关
    0.08
    ?q
    0.08
     alebo
    0.08
     किंवा
    0.08
    Activations Density 0.091%

    No Known Activations