© 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. 96775
    Prev
    Next
    INDEX
    Explanations

    ал

    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
     D
    -0.08
    -nine
    -0.07
    ాగా
    -0.07
    -.
    -0.07
    -two
    -0.07
     Nine
    -0.07
     .
    -0.07
    .D
    -0.07
     cread
    -0.07
    a
    -0.07
    POSITIVE LOGITS
    ambani
    0.10
    ләрни
    0.09
     watoto
    0.09
     დაუ�
    0.09
     хлоп
    0.09
     cupcakes
    0.09
     урын
    0.09
    λημα
    0.09
    ωνισ
    0.09
    τω
    0.09
    Activations Density 0.001%

    No Known Activations