© 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. 48033
    Prev
    Next
    INDEX
    Explanations

    Sim

    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
     better
    -0.11
     bedre
    -0.10
     basic
    -0.09
    better
    -0.09
    基本
    -0.09
    .basic
    -0.09
     tighter
    -0.09
    basic
    -0.09
    Basic
    -0.09
     tightly
    -0.09
    POSITIVE LOGITS
     Sim
    0.38
     simplicité
    0.32
     simplic
    0.30
     eenvoud
    0.29
    simp
    0.28
     સરળ
    0.28
    Sim
    0.28
     liht
    0.27
    sim
    0.26
     সহজ
    0.26
    Activations Density 0.085%

    No Known Activations