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. 11614
    Prev
    Next
    INDEX
    Explanations

    Code dependencies and frameworks

    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
     nucle
    -0.08
     Mee
    -0.08
     Thi
    -0.08
    _degree
    -0.07
     Florida
    -0.07
     Gav
    -0.07
     unrestricted
    -0.07
     drastic
    -0.07
    _TOTAL
    -0.07
     (*
    -0.07
    POSITIVE LOGITS
    -mail
    0.09
     scaff
    0.08
    Mail
    0.08
    _mail
    0.08
     paiement
    0.08
    asonry
    0.08
     warn
    0.08
     vieles
    0.08
     alert
    0.08
     terminar
    0.08
    Activations Density 0.006%

    No Known Activations