© 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. 3-RESID-POST-AA
    11. 2790
    Prev
    Next
    INDEX
    Explanations

    响

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rolling
    -0.08
    ā
    -0.07
     aet
    -0.07
    amas
    -0.07
    ü
    -0.07
    -0.07
     blessing
    -0.07
    ontology
    -0.07
     Myself
    -0.07
    ಾದ
    -0.07
    POSITIVE LOGITS
    740
    0.09
     فإنه
    0.08
     δι
    0.08
    ക്ട
    0.08
    elsk
    0.08
     geldt
    0.08
     nectar
    0.08
     trat
    0.08
    Earn
    0.07
     commander
    0.07
    Activations Density 0.000%
    No Known Activations