© 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. 23-RESID-POST-AA
    11. 48065
    Prev
    Next
    INDEX
    Explanations

    Aug

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    723
    -0.11
    。：
    -0.10
     sogenannte
    -0.10
     Первый
    -0.10
    710
    -0.09
    624
    -0.09
    -“
    -0.09
    726
    -0.09
    -Speed
    -0.09
     Taus
    -0.09
    POSITIVE LOGITS
    Table
    0.08
    Personnel
    0.08
    Address
    0.08
    Relationship
    0.08
    Ph
    0.08
    Name
    0.08
    Def
    0.08
    Service
    0.08
     ability
    0.08
    Plane
    0.08
    Activations Density 0.009%

    No Known Activations