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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97478
    Prev
    Next
    INDEX
    Explanations

    including, containing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remain
    -0.08
     find
    -0.08
     there's
    -0.08
     creare
    -0.08
     obtain
    -0.08
    #create
    -0.08
     finde
    -0.08
     remained
    -0.08
     создания
    -0.07
     feststellen
    -0.07
    POSITIVE LOGITS
    包含
    0.33
    涵
    0.32
    包括
    0.29
    涉及
    0.27
     beinhaltet
    0.27
     omvat
    0.27
     включает
    0.27
     umfasst
    0.27
     تشمل
    0.27
     encompassing
    0.26
    Activations Density 0.086%

    No Known Activations