© 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. 5927
    Prev
    Next
    INDEX
    Explanations

    Car models and Japanese references

    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
    Donalds
    -0.09
    uky
    -0.08
    árm
    -0.08
    aule
    -0.08
    donald
    -0.08
     বহ
    -0.08
     nuclé
    -0.08
    axi
    -0.08
    engwa
    -0.07
    mult
    -0.07
    POSITIVE LOGITS
     HR
    0.08
     CR
    0.08
     AIR
    0.08
     abak
    0.08
    186
    0.07
     convierte
    0.07
    シリーズ
    0.07
     podcast
    0.07
     LEG
    0.07
     HIV
    0.07
    Activations Density 0.001%

    No Known Activations