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. 12607
    Prev
    Next
    INDEX
    Explanations

    blockchain technology

    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
     einsetzen
    -0.08
     Gtk
    -0.08
     Untersuchung
    -0.08
     Enter
    -0.08
     महिला
    -0.08
     Jet
    -0.08
     қала
    -0.08
    лады
    -0.08
     Girl
    -0.07
     ವಿದ್ಯಾರ್ಥ
    -0.07
    POSITIVE LOGITS
     iterative
    0.10
     hacker
    0.09
     relentless
    0.09
     impartial
    0.09
     citer
    0.09
     immutable
    0.09
     infatti
    0.08
     irreversible
    0.08
     algorithms
    0.08
    Algorithms
    0.08
    Activations Density 0.009%

    No Known Activations