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. 44231
    Prev
    Next
    INDEX
    Explanations

    ~

    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
     Hastings
    -0.07
    strand
    -0.07
    fw
    -0.07
     ont
    -0.07
    업
    -0.07
     �
    -0.07
     somehow
    -0.07
    otus
    -0.07
    牌
    -0.07
     crystalline
    -0.07
    POSITIVE LOGITS
    imate
    0.08
    ≈
    0.08
     molecule
    0.07
    否
    0.07
    ipop
    0.07
    nak
    0.07
     contest
    0.07
     selecting
    0.07
    thol
    0.07
     Eup
    0.07
    Activations Density 0.028%

    No Known Activations