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. 90692
    Prev
    Next
    INDEX
    Explanations

    numerical data and articles

    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
     perd
    -0.08
     Hook
    -0.08
    Hook
    -0.08
     Hobby
    -0.08
     hook
    -0.08
     perdu
    -0.08
     wield
    -0.08
    Kick
    -0.07
     crowdfunding
    -0.07
    _SPACE
    -0.07
    POSITIVE LOGITS
     facts
    0.10
    Facts
    0.09
     तथ
    0.09
    _fact
    0.08
    facts
    0.08
     Facts
    0.08
     तथ्य
    0.08
     feiten
    0.08
    batim
    0.08
    事实
    0.08
    Activations Density 0.218%

    No Known Activations