© 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. 11-RESID-POST-AA
    11. 26508
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sz
    -0.08
     hol
    -0.07
     Hol
    -0.07
    Sz
    -0.07
     encompassing
    -0.07
     scattered
    -0.07
    DNS
    -0.07
     guidelines
    -0.06
    Hol
    -0.06
    erdem
    -0.06
    POSITIVE LOGITS
     cav
    0.08
     �
    0.08
     invitados
    0.08
    减
    0.08
    減
    0.08
     ઘટાડ
    0.08
     funzion
    0.08
    _reduce
    0.08
     tactic
    0.08
     impair
    0.07
    Activations Density 0.040%

    No Known Activations