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. 60470
    Prev
    Next
    INDEX
    Explanations

    cream

    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
    CGRect
    -0.09
     komm
    -0.07
    law
    -0.07
    Law
    -0.07
    Cupid
    -0.07
    Https
    -0.07
    66
    -0.07
    _campaign
    -0.07
    cum
    -0.07
    cab
    -0.07
    POSITIVE LOGITS
     Jason
    0.08
    qh
    0.07
     mott
    0.07
     Selle
    0.07
     accidental
    0.07
    ಟ್
    0.07
     س
    0.07
    essione
    0.07
    ಾಪ
    0.07
     Aer
    0.07
    Activations Density 0.021%

    No Known Activations