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. 67174
    Prev
    Next
    INDEX
    Explanations

    Expressing possibility/necessity

    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
     quindi
    -0.10
    なので
    -0.09
     thus
    -0.08
     więc
    -0.08
     vst
    -0.08
    thus
    -0.08
     Под
    -0.08
    복
    -0.08
     હોવાથી
    -0.07
     entretanto
    -0.07
    POSITIVE LOGITS
    ware
    0.08
    forth
    0.08
    �
    0.08
    乎
    0.08
    炎
    0.07
    Firstly
    0.07
    �
    0.07
     অক্টোবর
    0.07
    രു
    0.07
     tentativa
    0.07
    Activations Density 0.130%

    No Known Activations