© 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. 96956
    Prev
    Next
    INDEX
    Explanations

    à

    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
     entspricht
    -0.09
     basiert
    -0.09
     recognition
    -0.08
    hnung
    -0.08
     spielt
    -0.08
     beetje
    -0.08
     тро
    -0.07
     stammt
    -0.07
     voldoet
    -0.07
    umble
    -0.07
    POSITIVE LOGITS
     retenir
    0.14
     reten
    0.10
     هنگام
    0.09
     garder
    0.09
     maîtr
    0.09
     Sur
    0.09
     Ret
    0.08
     ressalt
    0.08
     Mait
    0.08
     surfaces
    0.08
    Activations Density 0.002%

    No Known Activations