© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129457
    Prev
    Next
    INDEX
    Explanations

    Book excerpts

    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
     neoliberal
    -0.10
    _idx
    -0.09
     archiv
    -0.09
    _idxs
    -0.09
     архив
    -0.08
    :innen
    -0.08
     archived
    -0.08
     archae
    -0.08
     cybersecurity
    -0.07
     archival
    -0.07
    POSITIVE LOGITS
    automatic
    0.08
     automatique
    0.08
     Automatic
    0.08
     bisherigen
    0.08
    Automatic
    0.08
     automatic
    0.08
     Monsieur
    0.08
     setw
    0.08
    APPLICATION
    0.08
     AUTOM
    0.08
    Activations Density 0.159%

    No Known Activations